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

    Neuronpedia

    INDEX
    Explanations

    Nullable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     زمان
    -0.08
     مرا
    -0.08
     Wedding
    -0.08
     dictators
    -0.08
     вақти
    -0.08
     वडा
    -0.08
     drown
    -0.07
     maturity
    -0.07
    ρωση
    -0.07
     {}),↵
    -0.07
    POSITIVE LOGITS
    cripts
    0.10
    .parameter
    0.07
    整数
    0.07
     Cialis
    0.07
    기에
    0.07
     suppression
    0.07
    Crunch
    0.07
     personnalis
    0.07
    avers
    0.07
     прес
    0.07
    Act Density 0.001%

    No Known Activations