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

    Neuronpedia

    INDEX
    Explanations

    ayudar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vect
    -0.07
     gore
    -0.07
    ást
    -0.07
    -actions
    -0.07
    がお
    -0.06
    .Un
    -0.06
    iffany
    -0.06
    ณะ
    -0.06
    -､
    -0.06
     Creature
    -0.06
    POSITIVE LOGITS
    eyJ
    0.07
    емон
    0.07
    sometimes
    0.07
     kanal
    0.06
    -ln
    0.06
     khỏ
    0.06
     helping
    0.06
    educ
    0.06
    getActiveSheet
    0.06
    Hints
    0.06
    Act Density 0.011%

    No Known Activations