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

    Neuronpedia

    INDEX
    Explanations

    technical commands and specific software functionality

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

    Code, data, or configuration snippets

    np_acts-logits-general · gemini-2.0-flash

    compound technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الحره
    -0.88
    sizeCache
    -0.81
    -------
    -0.77
     <<<<<<<<<<<<<<
    -0.74
    İstinadlar
    -0.72
    Enllaços
    -0.67
     GreatSchools
    -0.65
    Šaltiniai
    -0.65
    featureID
    -0.65
    aliana
    -0.64
    POSITIVE LOGITS
    _
    0.60
    TagMode
    0.58
    ſtanding
    0.50
     *_
    0.47
    ware
    0.47
    いかが
    0.47
    }></
    0.47
    ...@
    0.47
    gridx
    0.47
    wige
    0.46
    Act Density 0.482%

    No Known Activations