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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shouldBe
    -0.07
    .F
    -0.06
     messageId
    -0.06
     Oliveira
    -0.06
     Gol
    -0.06
    /hooks
    -0.06
     folded
    -0.06
     Zu
    -0.06
    classnames
    -0.06
    FE
    -0.06
    POSITIVE LOGITS
     Leakage
    0.07
     Greek
    0.07
     Econom
    0.07
    cdf
    0.07
    .beginTransaction
    0.07
    =out
    0.07
     slim
    0.06
    fine
    0.06
    staff
    0.06
    .workspace
    0.06
    Act Density 0.007%

    No Known Activations