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

    Neuronpedia

    INDEX
    Explanations

    take

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opat
    -0.08
    Bus
    -0.07
    California
    -0.07
     California
    -0.07
     compromising
    -0.07
     民
    -0.07
    Store
    -0.06
     kıs
    -0.06
    Pakistan
    -0.06
     SEM
    -0.06
    POSITIVE LOGITS
     темп
    0.07
     erót
    0.06
    dd
    0.06
    inned
    0.06
     office
    0.06
     mělo
    0.06
    oruč
    0.06
    indsight
    0.06
    URITY
    0.06
     міль
    0.06
    Act Density 0.021%

    No Known Activations