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

    Neuronpedia

    INDEX
    Explanations

    transformations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crest
    -0.07
    -basic
    -0.07
    蚊
    -0.06
    אזור
    -0.06
    :@
    -0.06
    可视
    -0.06
    mnt
    -0.06
    Appro
    -0.06
    QR
    -0.06
    jsx
    -0.06
    POSITIVE LOGITS
     ensure
    0.08
    RARY
    0.07
     referencia
    0.07
     Gü
    0.07
    caled
    0.07
    赶赴
    0.07
     avaliações
    0.07
     lesbi
    0.06
    Erreur
    0.06
    eração
    0.06
    Act Density 0.425%

    No Known Activations