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

    Neuronpedia

    INDEX
    Explanations

    instances of critique and negative assessment

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

    financial or technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cold
    -0.31
     psicológico
    -0.30
     partid
    -0.30
     américa
    -0.30
     américains
    -0.27
     magis
    -0.27
     démocr
    -0.27
    upakan
    -0.26
     brace
    -0.26
    !')
    -0.26
    POSITIVE LOGITS
     informée
    0.67
    ########.
    0.66
    SharedDtor
    0.63
    MigrationBuilder
    0.61
    contentLoaded
    0.60
     <<<<<<<<<<<<<<
    0.60
    windowFixed
    0.60
    Diwedd
    0.58
     typelib
    0.58
    دانشنامهٔ
    0.58
    Act Density 0.081%

    No Known Activations