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

    Neuronpedia

    INDEX
    Explanations

    your own text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )。
    0.54
    𠃊
    0.50
    }$)
    0.48
    Real
    0.48
    ពេញ
    0.47
    }&\
    0.47
    State
    0.46
    Queen
    0.46
    Healthy
    0.46
    }$).
    0.46
    POSITIVE LOGITS
    unun
    0.47
     kini
    0.47
    adto
    0.45
     lapisan
    0.44
     पवन
    0.42
     pank
    0.42
    াতে
    0.41
    teman
    0.40
     activity
    0.40
    adan
    0.39
    Act Density 0.000%

    No Known Activations