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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Patrick
    -0.07
    بيرة
    -0.07
     zamanda
    -0.06
     INTERNATIONAL
    -0.06
    říklad
    -0.06
    Berry
    -0.06
     ”↵
    -0.06
     PendingIntent
    -0.06
    Patrick
    -0.06
    _cipher
    -0.06
    POSITIVE LOGITS
    .
    0.11
    ).
    0.09
    .\
    0.08
    .T
    0.08
    .
    0.08
    .D
    0.08
    ..
    0.08
    .M
    0.08
    ा.
    0.08
    |.
    0.07
    Act Density 0.142%

    No Known Activations