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

    Neuronpedia

    INDEX
    Explanations

    energy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +')
    -0.07
    according
    -0.06
    optimized
    -0.06
    нике
    -0.06
    noc
    -0.06
    inclu
    -0.06
    IRROR
    -0.06
     Дмит
    -0.06
    .Thread
    -0.06
    Wire
    -0.06
    POSITIVE LOGITS
    ({'
    0.07
     başarı
    0.07
     lingu
    0.07
     divul
    0.06
     сохран
    0.06
    _INITIAL
    0.06
     پش
    0.06
     culprit
    0.06
    ">//
    0.06
     Croatian
    0.06
    Act Density 0.047%

    No Known Activations