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

    Neuronpedia

    INDEX
    Explanations

    diverse texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Chat
    -0.07
     nanny
    -0.07
     жал
    -0.07
     reportedly
    -0.06
    urations
    -0.06
    ret
    -0.06
     favourite
    -0.06
    َب
    -0.06
    ادم
    -0.06
     Stretch
    -0.06
    POSITIVE LOGITS
    fieldName
    0.07
    (id
    0.06
    SUCCESS
    0.06
    fuse
    0.06
    (metadata
    0.06
    _avatar
    0.06
    (statement
    0.06
     roots
    0.06
     Georges
    0.06
     flere
    0.06
    Act Density 0.000%

    No Known Activations