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

    Neuronpedia

    INDEX
    Explanations

    explanations and how things work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Send
    -0.07
    óm
    -0.06
     Zusammen
    -0.06
    .mime
    -0.06
    шки
    -0.06
     Louise
    -0.06
     hud
    -0.06
    吃
    -0.06
     forgetting
    -0.06
     bella
    -0.06
    POSITIVE LOGITS
    ibili
    0.07
    (",",
    0.07
    ?v
    0.07
     Wich
    0.07
     ее
    0.06
     SetLastError
    0.06
    _Event
    0.06
    각
    0.06
    (TypeError
    0.06
     GL
    0.06
    Act Density 0.313%

    No Known Activations