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

    Neuronpedia

    INDEX
    Explanations

    form or century

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Aug
    0.82
     Aug
    0.72
    ង
    0.72
     autoradi
    0.69
    Casa
    0.69
    uke
    0.67
    Sept
    0.67
     tert
    0.65
     ibu
    0.65
     Seems
    0.65
    POSITIVE LOGITS
     form
    0.95
     forms
    0.81
     century
    0.78
    form
    0.73
    formen
    0.72
     ফর্ম
    0.70
     forma
    0.68
     centuries
    0.67
    forms
    0.65
     Forms
    0.64
    Act Density 0.030%

    No Known Activations