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

    Neuronpedia

    INDEX
    Explanations

    to know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    1.60
    o
    1.49
    k
    1.46
    ことを
    1.41
    न
    1.41
     sendo
    1.40
    การ
    1.38
     dieses
    1.33
    на
    1.33
    g
    1.31
    POSITIVE LOGITS
    ppled
    1.54
    BAC
    1.53
    asting
    1.52
    ppling
    1.46
    othed
    1.46
    𝐞
    1.31
     μην
    1.26
    oting
    1.23
     वहीं
    1.22
    бліоте
    1.22
    Act Density 0.677%

    No Known Activations