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

    Neuronpedia

    INDEX
    Explanations

    code and shame

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     might
    0.37
    俑
    0.37
    नावश्यक
    0.37
    的时候
    0.35
    TERMIN
    0.35
    還要
    0.35
     بيان
    0.35
     neutrality
    0.35
    γέν
    0.35
     beau
    0.34
    POSITIVE LOGITS
    alahan
    0.45
    abil
    0.41
    hz
    0.40
    PTMR
    0.40
     ஒத்து
    0.40
    allel
    0.39
     एमएन
    0.38
    pyrazole
    0.38
    aginaw
    0.38
    நாதன்
    0.38
    Act Density 0.001%

    No Known Activations