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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мыш
    -0.07
     Drinks
    -0.07
    �
    -0.07
     "/
    -0.07
    vido
    -0.07
    -archive
    -0.06
    ="_
    -0.06
     ------------------------------------------------------------------------------------------------
    -0.06
     وزار
    -0.06
    gae
    -0.06
    POSITIVE LOGITS
    TP
    0.07
    지만
    0.06
    Trader
    0.06
    AY
    0.06
     를
    0.06
    >Email
    0.06
    Eb
    0.06
    IVERY
    0.06
     Predictor
    0.06
     питань
    0.06
    Act Density 0.000%

    No Known Activations