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

    Neuronpedia

    INDEX
    Explanations

    name three

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nol
    0.77
    ück
    0.75
    циа
    0.73
    ready
    0.73
     মুদ্রা
    0.71
    detach
    0.70
     pronta
    0.69
     contra
    0.68
    rump
    0.68
     பு
    0.68
    POSITIVE LOGITS
    plate
    1.17
    plates
    1.03
    PLATE
    0.93
    clature
    0.83
    करण
    0.80
    paced
    0.79
    WithOwner
    0.77
    囂
    0.75
    ंदगी
    0.74
    geving
    0.74
    Act Density 0.358%

    No Known Activations