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

    Neuronpedia

    INDEX
    Explanations

    wiley and willis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ва
    0.55
    tib
    0.55
    ியை
    0.54
    tive
    0.54
    ar
    0.53
    டையே
    0.51
    junction
    0.51
     worldRank
    0.51
    стве
    0.50
    দ্ভুত
    0.50
    POSITIVE LOGITS
    _
    0.56
    И
    0.56
    '
    0.55
    一
    0.53
     Prevalence
    0.52
    G
    0.51
    Α
    0.50
     soll
    0.50
    ವುದು
    0.50
    А
    0.50
    Act Density 0.000%

    No Known Activations