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

    Neuronpedia

    INDEX
    Explanations

    words starting with "Th"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kelig
    0.70
    hensible
    0.67
     الممل
    0.67
    женного
    0.65
     naked
    0.65
    ől
    0.64
     morgen
    0.64
     bare
    0.63
     Workers
    0.63
    抉
    0.63
    POSITIVE LOGITS
    oretical
    0.86
    iamine
    0.83
    alassemia
    0.82
    umping
    0.77
    rashed
    0.77
    èses
    0.75
    orough
    0.73
     çö
    0.73
    reonine
    0.73
    ㅔ
    0.72
    Act Density 0.041%

    No Known Activations