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

    Neuronpedia

    INDEX
    Explanations

    questions and phrases inquiring about extent or quantity

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

    Comes before "much" or "hard" or "indoctr"

    np_acts-logits-general · gemini-2.0-flash

    how explained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hjelp
    -0.59
     materiaal
    -0.56
     specchio
    -0.52
     beseech
    -0.51
     legyen
    -0.51
     borealis
    -0.51
     corretamente
    -0.51
     öner
    -0.51
     soient
    -0.50
     sanitarias
    -0.50
    POSITIVE LOGITS
    WHEREAS
    0.78
     autorytatywna
    0.74
    Aiheesta
    0.70
     how
    0.66
     चीज़ों
    0.66
    0.65
    ioutil
    0.64
     mergeFrom
    0.64
     much
    0.63
    ervant
    0.62
    Act Density 0.054%

    No Known Activations