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

    Neuronpedia

    INDEX
    Explanations

    profitability and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تحد
    0.53
     دائ
    0.47
     तेजी
    0.46
    cier
    0.46
     첨
    0.46
     మీ
    0.44
     প্রদ
    0.44
     అత
    0.44
     columnspan
    0.44
     व्यापक
    0.44
    POSITIVE LOGITS
    ট
    0.55
    ס
    0.52
    Ру
    0.49
    Calculate
    0.48
     ogrom
    0.48
    𝔀
    0.48
     Ice
    0.47
     élabor
    0.47
    "，
    0.47
    Ко
    0.46
    Act Density 0.000%

    No Known Activations