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

    Neuronpedia

    INDEX
    Explanations

    Features

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ROTO
    -0.07
    σκευή
    -0.07
    Pred
    -0.07
    bj
    -0.07
    _zones
    -0.07
    arb
    -0.06
    ٢
    -0.06
    IED
    -0.06
    кам
    -0.06
     زمانی
    -0.06
    POSITIVE LOGITS
     نگهد
    0.07
    _
↵
    0.06
    ToUpdate
    0.06
     เห
    0.06
     Ptr
    0.06
    Wenn
    0.06
     Namespace
    0.06
     rice
    0.06
    -progress
    0.06
     했
    0.06
    Act Density 0.098%

    No Known Activations