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

    Neuronpedia

    INDEX
    Explanations

    code/configuration files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ví
    -0.07
    minated
    -0.07
     horrific
    -0.07
    кое
    -0.07
    -L
    -0.07
    -services
    -0.06
     Liebe
    -0.06
    _pr
    -0.06
    에
    -0.06
    plings
    -0.06
    POSITIVE LOGITS
     phosphory
    0.06
    state
    0.06
    寺
    0.06
    plt
    0.06
     olmadığı
    0.06
     nargs
    0.06
     aktuellen
    0.06
    (one
    0.05
     EDGE
    0.05
    _Id
    0.05
    Act Density 0.010%

    No Known Activations