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

    Neuronpedia

    INDEX
    Explanations

    groups of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sur
    0.44
    *
    0.42
    模
    0.40
     cl
    0.38
     tempo
    0.36
     extra
    0.36
    T
    0.35
     gr
    0.35
    ap
    0.34
    @
    0.34
    POSITIVE LOGITS
     वनस्पती
    0.44
    வசாய
    0.43
     tumbuhan
    0.42
     Simplify
    0.42
    னிய
    0.42
     మొక్క
    0.42
     roślin
    0.42
    costcenter
    0.41
    benzoimidazole
    0.41
     تقسیم
    0.40
    Act Density 0.000%

    No Known Activations