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

    Neuronpedia

    INDEX
    Explanations

    identifying discrepancies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Credential
    0.54
    льзова
    0.46
     фаразы
    0.46
    镉
    0.45
    blur
    0.43
    リエステル
    0.42
     electrónico
    0.42
    Methoxy
    0.41
     километров
    0.41
     bụi
    0.41
    POSITIVE LOGITS
     dances
    0.46
     snd
    0.45
     Easter
    0.44
     Italy
    0.44
     winners
    0.43
     positive
    0.42
     excitement
    0.42
     fhall
    0.42
     winner
    0.42
     pride
    0.42
    Act Density 0.004%

    No Known Activations