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

    Neuronpedia

    INDEX
    Explanations

    github links for lm-sys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ⲃ
    0.48
    itudini
    0.38
    bukti
    0.37
    ecta
    0.37
    )).
    0.36
     Quốc
    0.36
     pras
    0.35
     हॉल
    0.35
    ^{+}$.
    0.35
     Broccoli
    0.35
    POSITIVE LOGITS
    LW
    0.39
    いだ
    0.39
    वि
    0.38
     بالم
    0.38
     ged
    0.37
     εν
    0.36
    ADC
    0.36
     확인함
    0.36
     neglect
    0.35
     மறு
    0.35
    Act Density 0.000%

    No Known Activations