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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ply
    -0.09
    Employment
    -0.08
     पद
    -0.08
    ообраз
    -0.08
     employs
    -0.08
     उद्योग
    -0.07
    angun
    -0.07
    Pwd
    -0.07
    нений
    -0.07
    ového
    -0.07
    POSITIVE LOGITS
     איך
    0.08
     boiled
    0.08
    'aide
    0.08
     revient
    0.08
     gostaria
    0.08
     worried
    0.08
     horrible
    0.07
     સારી
    0.07
     తెలుస
    0.07
     heater
    0.07
    Act Density 0.019%

    No Known Activations