Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to social and economic policies, particularly those involving subsidies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ending in "ing" converted to other endings

    np_acts-logits-general · gemini-2.0-flash

    negative actions and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.96
     "..\..\..\
    -0.86
    AutoScaleMode
    -0.75
    ★★★★☆
    -0.74
    webElementXpaths
    -0.73
     mergeFrom
    -0.72
     "..\..\
    -0.70
     EconPapers
    -0.70
    charCode
    -0.69
     deaktiviert
    -0.68
    POSITIVE LOGITS
    ſtra
    0.69
    ništ
    0.63
     détru
    0.61
    ſem
    0.60
     myö
    0.59
    yaszt
    0.58
    ésult
    0.58
    Pued
    0.56
     skjø
    0.54
     ruok
    0.54
    Act Density 0.981%

    No Known Activations