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

    Neuronpedia

    INDEX
    Explanations

    leave, rest, days, fund

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     de
    0.94
     aru
    0.89
    de
    0.86
     constituency
    0.85
     kary
    0.85
    מצא
    0.84
     jurisdiction
    0.84
     appellants
    0.82
     insurgency
    0.82
     plaintiffs
    0.81
    POSITIVE LOGITS
     wasnt
    0.95
    нуу
    0.86
    じ
    0.83
    였다
    0.82
    覚えて
    0.82
    でした
    0.79
     가서
    0.79
     동안
    0.78
    ımın
    0.77
     wasn
    0.76
    Act Density 0.123%

    No Known Activations