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

    Neuronpedia

    INDEX
    Explanations

    start of code or commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sarcoma
    0.79
    刬
    0.78
     werewolf
    0.77
    というか
    0.73
     câncer
    0.72
     gyárt
    0.71
    ずっと
    0.68
     பட்
    0.67
     ขั้น
    0.67
     supremacist
    0.67
    POSITIVE LOGITS
    не
    0.93
    on
    0.92
    те
    0.80
     termed
    0.74
    0.72
    с
    0.70
    ა
    0.70
    am
    0.70
    ни
    0.70
    X
    0.69
    Act Density 0.001%

    No Known Activations