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

    Neuronpedia

    INDEX
    Explanations

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     meningitis
    0.87
     Sanger
    0.86
     cuffs
    0.85
     cytoskeleton
    0.84
     moratorium
    0.82
     intran
    0.82
     hamster
    0.82
     PLHIV
    0.82
     baik
    0.82
     individuais
    0.82
    POSITIVE LOGITS
    Legend
    0.87
    তে
    0.78
    Portugal
    0.77
     zdjęcia
    0.77
    that
    0.77
    According
    0.77
    Anyone
    0.76
    Let
    0.75
    Quarter
    0.75
    根據
    0.74
    Act Density 0.001%

    No Known Activations