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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    weakSelf
    -0.07
    ケース
    -0.07
     Lawyer
    -0.06
     realization
    -0.06
    iliary
    -0.06
     forgotten
    -0.06
    toc
    -0.06
     Abbott
    -0.06
     McCartney
    -0.06
     mois
    -0.06
    POSITIVE LOGITS
     hack
    0.06
     OAuth
    0.06
    を開
    0.06
    (end
    0.06
     conforme
    0.06
    (fieldName
    0.06
    atican
    0.06
    .Account
    0.06
    ordin
    0.06
     outing
    0.06
    Act Density 0.000%

    No Known Activations