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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    碼
    -0.07
     demonstration
    -0.07
    вар
    -0.07
     contractor
    -0.06
     Mothers
    -0.06
    ิป
    -0.06
     messages
    -0.06
     trộn
    -0.06
     бактер
    -0.06
     FROM
    -0.06
    POSITIVE LOGITS
     ortadan
    0.07
    ("");
    0.07
     breathe
    0.06
    )];
↵
    0.06
    ')]↵
    0.06
    .imwrite
    0.06
    _REAL
    0.06
    }),
    0.06
     swung
    0.06
     lég
    0.06
    Act Density 0.050%

    No Known Activations