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

    Neuronpedia

    INDEX
    Explanations

    survived

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Height
    -0.06
     accountant
    -0.06
    Helpers
    -0.06
    OrCreate
    -0.06
    委員
    -0.06
    -mouth
    -0.06
     Go
    -0.06
    Submitting
    -0.06
    _H
    -0.06
     adm
    -0.06
    POSITIVE LOGITS
     Skyl
    0.07
     anticipate
    0.07
    اعة
    0.06
    (vars
    0.06
     öldür
    0.06
    .and
    0.06
    (criteria
    0.06
     RootState
    0.06
     Checked
    0.06
    완료
    0.06
    Act Density 0.001%

    No Known Activations