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

    Neuronpedia

    INDEX
    Explanations

    hydrocarbon liquids or refrigerants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    1.00
    기
    0.79
     і
    0.79
    is
    0.79
    ма
    0.78
     да
    0.74
     ს
    0.71
     opinião
    0.71
    dois
    0.71
    макра
    0.70
    POSITIVE LOGITS
     on
    0.80
    v
    0.75
    ancy
    0.57
     and
    0.55
    hatt
    0.55
    frist
    0.55
    endoza
    0.54
     exceptions
    0.54
    oya
    0.54
    ovat
    0.53
    Act Density 0.001%

    No Known Activations