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

    Neuronpedia

    INDEX
    Explanations

    `-f` then filename

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inaugural
    0.43
     ресу
    0.42
     измерения
    0.41
     заболе
    0.41
     Hazrat
    0.41
     CONSTRAINT
    0.40
     chống
    0.40
     между
    0.40
     errMsg
    0.40
    <unused2040>
    0.39
    POSITIVE LOGITS
    k
    0.51
    ek
    0.48
    isk
    0.47
    il
    0.47
    man
    0.47
    ud
    0.47
    j
    0.47
    ad
    0.45
    car
    0.44
    z
    0.44
    Act Density 0.001%

    No Known Activations