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

    Neuronpedia

    INDEX
    Explanations

    technical instructions and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Service
    0.43
    ın
    0.43
     zákaz
    0.43
    ahrer
    0.43
     wanna
    0.42
     painter
    0.41
     değer
    0.41
     datang
    0.40
     behest
    0.40
    服務
    0.40
    POSITIVE LOGITS
     насеко
    0.47
    oughton
    0.44
    inetics
    0.42
    бия
    0.42
     организма
    0.42
    MaxIntensity
    0.42
    संत
    0.41
     खोला
    0.41
    ubation
    0.41
     तुलसी
    0.41
    Act Density 0.004%

    No Known Activations