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

    Neuronpedia

    INDEX
    Explanations

    qualifications and alternatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     animal
    -0.08
    -month
    -0.07
    oped
    -0.07
     inhabited
    -0.07
     Empire
    -0.07
    -out
    -0.07
    Authenticated
    -0.07
     disposal
    -0.07
     sees
    -0.07
    enser
    -0.06
    POSITIVE LOGITS
    .tencent
    0.06
     Undo
    0.06
    .↵↵↵↵↵↵↵↵↵↵
    0.06
    (interp
    0.06
     victorious
    0.06
    dcc
    0.06
    _View
    0.05
    #![
    0.05
    ㎡
    0.05
    Directive
    0.05
    Act Density 0.060%

    No Known Activations