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

    Neuronpedia

    INDEX
    Explanations

    scientific journal articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     temptation
    -0.07
    MMdd
    -0.07
    ываем
    -0.07
     예수님
    -0.07
    Подроб
    -0.07
    過程中
    -0.07
     IPP
    -0.06
     الإنسان
    -0.06
    חלום
    -0.06
     btnSave
    -0.06
    POSITIVE LOGITS
    _corners
    0.07
    �
    0.07
    _workers
    0.07
     quant
    0.07
    勋
    0.07
    =$
    0.07
    빅
    0.07
    ALE
    0.07
    SR
    0.07
     matching
    0.07
    Act Density 0.020%

    No Known Activations