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

    Neuronpedia

    INDEX
    Explanations

    words starting with mar

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ťaž
    1.04
    ential
    1.00
     Packed
    0.94
    রকম
    0.94
    ⁿ
    0.94
     strict
    0.93
     maybe
    0.93
    factor
    0.92
    memset
    0.91
    ents
    0.90
    POSITIVE LOGITS
     Madness
    1.52
    smanship
    1.46
     dépos
    1.35
     Twain
    1.30
    шал
    1.30
     registrada
    1.23
    igold
    1.23
    riott
    1.23
    主体
    1.21
    tpl
    1.19
    Act Density 0.141%

    No Known Activations