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

    Neuronpedia

    INDEX
    Explanations

    technical file formats and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    សម
    0.43
     subgroup
    0.42
     deviates
    0.39
     AMS
    0.38
    ക്കാം
    0.38
     subgroups
    0.37
     appro
    0.36
     subclass
    0.35
    が高
    0.35
    vek
    0.35
    POSITIVE LOGITS
    uración
    0.43
    atiya
    0.43
    烈
    0.43
    ÓN
    0.42
    陋
    0.41
     कटा
    0.40
    ദ്ദേ
    0.40
    贸
    0.40
    骇
    0.39
     বণ্ট
    0.38
    Act Density 0.000%

    No Known Activations