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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SCALE
    -0.06
     HOH
    -0.06
    ूत
    -0.06
     paylaş
    -0.06
    icide
    -0.06
    orgetown
    -0.06
     기타
    -0.06
    เจร
    -0.06
    ’in
    -0.06
     Assass
    -0.06
    POSITIVE LOGITS
    |↵
    0.08
    唯一
    0.07
    }`↵
    0.07
    .Sh
    0.06
    ！');↵
    0.06
    ptive
    0.06
    ))?
    0.06
    illian
    0.06
     cardinal
    0.06
     Bray
    0.06
    Act Density 0.000%

    No Known Activations