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

    Neuronpedia

    INDEX
    Explanations

    Legal/court documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     activate
    -0.07
     ~
    -0.07
     computers
    -0.06
     supremacist
    -0.06
     Computes
    -0.06
     empres
    -0.06
     suppression
    -0.06
     deposits
    -0.06
     mood
    -0.06
    .Created
    -0.06
    POSITIVE LOGITS
     Invocation
    0.06
    ž
    0.06
    팅
    0.06
    _FINISH
    0.06
    ButtonTitles
    0.06
     내
    0.06
     loosen
    0.06
     reordered
    0.06
    _Form
    0.06
    جد
    0.06
    Act Density 0.003%

    No Known Activations