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

    Neuronpedia

    INDEX
    Explanations

    Word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     находятся
    -0.09
     Bildungs
    -0.08
     petr
    -0.08
    נסות
    -0.08
    immune
    -0.08
     пород
    -0.08
    andung
    -0.08
     ESR
    -0.08
    möglichkeiten
    -0.07
    OLAR
    -0.07
    POSITIVE LOGITS
    _needed
    0.11
    Needed
    0.11
     lazım
    0.10
    _used
    0.10
    Used
    0.10
    EEDED
    0.10
     diperlukan
    0.09
    用于
    0.09
    必要
    0.09
     potrzeb
    0.09
    Act Density 0.032%

    No Known Activations