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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    THOOK
    -0.07
    (new
    -0.07
     betting
    -0.07
     tw
    -0.06
    Inv
    -0.06
     reward
    -0.06
    Gun
    -0.06
     Dise
    -0.06
     sons
    -0.06
     Arr
    -0.06
    POSITIVE LOGITS
    _reserve
    0.06
    ayas
    0.06
    ظة
    0.06
    єн
    0.06
    fecha
    0.06
    cla
    0.06
    PosY
    0.06
     vš
    0.06
    ManagedObject
    0.06
    .StatusCode
    0.05
    Act Density 0.011%

    No Known Activations