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

    Neuronpedia

    INDEX
    Explanations

    identifiable, identifiers, identities, identical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    まして
    0.41
     nhàng
    0.41
    )^{*
    0.41
    امہ
    0.40
     словам
    0.40
     ajustes
    0.40
    ್ಯಾ
    0.39
     Salvatore
    0.39
     gastos
    0.38
    gher
    0.38
    POSITIVE LOGITS
     identified
    0.70
    identified
    0.67
     Identified
    0.66
     identifiable
    0.63
     identifiers
    0.61
     IDENT
    0.59
    IDENT
    0.58
     indent
    0.54
    Ident
    0.53
     identifier
    0.53
    Act Density 0.004%

    No Known Activations