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

    Neuronpedia

    INDEX
    Explanations

    hell and hellish forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    allas
    0.45
    OUSE
    0.38
    ালের
    0.38
     SUPPLY
    0.37
    alles
    0.37
    allus
    0.37
    iddag
    0.37
    豈
    0.36
     tble
    0.36
    မီ
    0.36
    POSITIVE LOGITS
     hell
    0.86
    Hell
    0.77
     Hell
    0.73
    ishly
    0.69
    ish
    0.68
    hell
    0.62
    hound
    0.62
    uva
    0.60
    hounds
    0.60
     bent
    0.59
    Act Density 0.012%

    No Known Activations