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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nep
    -0.07
     convinced
    -0.07
     Hopkins
    -0.06
    isel
    -0.06
    ur
    -0.06
    isk
    -0.06
    ип
    -0.06
    捷
    -0.06
    ennessee
    -0.06
    UR
    -0.06
    POSITIVE LOGITS
    ("""
    0.07
    (ll
    0.07
     kvinnor
    0.06
    ？」↵↵
    0.06
    -muted
    0.06
    .";
↵
    0.06
    办法
    0.06
    "';↵
    0.06
     рівні
    0.06
    надлеж
    0.06
    Act Density 0.353%

    No Known Activations