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

    Neuronpedia

    INDEX
    Explanations

    passion, Pascal, password

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    yect
    0.44
    堺
    0.43
    peror
    0.40
    velop
    0.39
    hle
    0.39
    źni
    0.39
    remely
    0.38
    ractive
    0.38
    thank
    0.38
    plements
    0.38
    POSITIVE LOGITS
     passive
    0.80
     Passive
    0.73
    Passive
    0.70
     pas
    0.66
     passively
    0.65
     Pass
    0.60
     पासवान
    0.59
    passive
    0.59
     Pas
    0.58
     passivation
    0.58
    Act Density 0.015%

    No Known Activations