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

    Neuronpedia

    INDEX
    Explanations

    multi-factor authentication

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gawa
    0.38
     temporary
    0.38
    asional
    0.38
     grove
    0.38
    ЕМ
    0.37
     lip
    0.37
     Temporary
    0.37
     halogen
    0.36
     Larry
    0.36
    andinavian
    0.35
    POSITIVE LOGITS
     MFA
    0.47
    authentication
    0.41
    Authentication
    0.41
    ා
    0.41
     Authentication
    0.38
     बॉय
    0.38
    Authenticator
    0.38
     Bunker
    0.37
     vattati
    0.36
    authenticate
    0.36
    Act Density 0.013%

    No Known Activations