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

    Neuronpedia

    INDEX
    Explanations

    descriptions of things

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     realiza
    0.61
     VIP
    0.59
     Tahiti
    0.59
     kra
    0.58
     ál
    0.58
    LJ
    0.56
     LJ
    0.55
    hend
    0.55
     wię
    0.55
    JKL
    0.54
    POSITIVE LOGITS
     Characteristic
    0.59
     Charity
    0.57
    characteristic
    0.55
    schemaName
    0.55
    _[
    0.53
     एक्सप्ले
    0.53
    collections
    0.52
    characters
    0.52
    ElementName
    0.52
    Characteristic
    0.51
    Act Density 0.000%

    No Known Activations