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

    Neuronpedia

    INDEX
    Explanations

    otros

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     being
    0.47
    ávat
    0.46
    و
    0.45
     ساختمان
    0.45
     THEM
    0.44
     ठेवा
    0.44
    クセル
    0.44
     být
    0.43
    訛
    0.43
     dítě
    0.43
    POSITIVE LOGITS
    haul
    0.48
     unang
    0.46
     agh
    0.46
    agan
    0.45
     Angaben
    0.45
     полу
    0.43
    abre
    0.43
     kard
    0.43
    urut
    0.42
    Ricky
    0.42
    Act Density 0.000%

    No Known Activations