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

    Neuronpedia

    INDEX
    Explanations

    supportive context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ีด
    1.07
     arbitr
    1.04
    싶
    0.98
    کرد
    0.98
     الفر
    0.97
    ுண்டு
    0.95
    мал
    0.95
    ти
    0.94
     surprise
    0.93
    મો
    0.93
    POSITIVE LOGITS
    ActionBar
    1.09
     принятия
    1.03
    Titan
    1.00
     স্টাফ
    0.98
     beams
    0.97
     penuh
    0.96
     Staffordshire
    0.95
     estructuras
    0.95
    力度
    0.95
    प्रमुख
    0.93
    Act Density 0.111%

    No Known Activations