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

    Neuronpedia

    INDEX
    Explanations

    mathematical context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ').↵
    -0.08
    lost
    -0.07
    .Named
    -0.06
    در
    -0.06
    '.↵
    -0.06
    .isfile
    -0.06
     arrive
    -0.06
     shining
    -0.06
    leans
    -0.06
     gilt
    -0.06
    POSITIVE LOGITS
    ειτουργ
    0.07
    .Audio
    0.06
    -backend
    0.06
     obstruct
    0.06
     voks
    0.06
     وزن
    0.06
     смер
    0.06
     Κατηγορία
    0.06
     Ner
    0.06
    ButtonType
    0.06
    Act Density 0.018%

    No Known Activations