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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Preservation
    -0.08
     Sacr
    -0.07
     Real
    -0.07
    .Max
    -0.07
     Cup
    -0.07
     Championship
    -0.07
    parentId
    -0.07
    Frozen
    -0.06
    Insets
    -0.06
     attacked
    -0.06
    POSITIVE LOGITS
    ЙЙ
    0.06
     відмов
    0.06
     GPI
    0.06
     commit
    0.06
     disables
    0.06
    _stride
    0.06
     ديگر
    0.06
    PLAIN
    0.06
     ntohs
    0.06
    iskey
    0.05
    Act Density 0.043%

    No Known Activations