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

    Neuronpedia

    INDEX
    Explanations

    words related to the expression of disapproval

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xase
    -0.63
    MathML
    -0.52
    RO
    -0.50
    Event
    -0.50
    erol
    -0.50
     dung
    -0.50
    era
    -0.49
    Se
    -0.48
     zaz
    -0.48
    o
    -0.47
    POSITIVE LOGITS
     Critics
    1.09
    Critic
    1.02
     Criticism
    0.99
     ExecuteAsync
    0.97
     Critic
    0.96
     "..\..\
    0.90
    Critics
    0.90
     ***!
    0.88
     critics
    0.88
     criticism
    0.86
    Act Density 0.006%

    No Known Activations