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

    Neuronpedia

    INDEX
    Explanations

    she

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LCD
    -0.07
     projects
    -0.07
    boy
    -0.07
     channels
    -0.07
     Rug
    -0.07
    Small
    -0.06
     taxis
    -0.06
    をする
    -0.06
     praises
    -0.06
    -Nazi
    -0.06
    POSITIVE LOGITS
    ...↵↵↵
    0.07
    /her
    0.07
    .
↵
    0.06
    /she
    0.06
     belirli
    0.06
    /Delete
    0.06
    vable
    0.06
    ':↵↵
    0.06
    $count
    0.06
     เ�
    0.06
    Act Density 0.004%

    No Known Activations