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

    Neuronpedia

    INDEX
    Explanations

    read the notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sank
    0.52
     psychologist
    0.51
     Psychologist
    0.51
     announcement
    0.50
     సంగ
    0.49
    प्टन
    0.48
    渓
    0.47
    ຯ
    0.46
     vonat
    0.46
     sót
    0.46
    POSITIVE LOGITS
    ritu
    0.71
     tweak
    0.70
     एवं
    0.69
    क्ले
    0.66
    withProperties
    0.65
     mangle
    0.63
    lmfit
    0.63
     limp
    0.62
    పోయే
    0.62
     clichés
    0.61
    Act Density 0.008%

    No Known Activations