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

    Neuronpedia

    INDEX
    Explanations

    password

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    overlay
    -0.07
    _F
    -0.06
     Arb
    -0.06
    _w
    -0.06
     ep
    -0.06
    롭
    -0.06
    Google
    -0.06
    arya
    -0.06
    acet
    -0.06
     неп
    -0.06
    POSITIVE LOGITS
    -looking
    0.07
    fts
    0.06
     mehr
    0.06
     bulls
    0.06
     Hector
    0.06
    bage
    0.06
    endar
    0.06
     zab
    0.06
    (instance
    0.06
    _stuff
    0.06
    Act Density 0.008%

    No Known Activations