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

    Neuronpedia

    INDEX
    Explanations

    dynamic programming and range

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ྃ
    0.51
    纾
    0.49
    われ
    0.46
    roon
    0.46
    ی
    0.46
    था
    0.45
     authored
    0.45
    ﻘ
    0.45
    त्र
    0.44
    लि
    0.43
    POSITIVE LOGITS
     verzi
    0.52
     букмекердик
    0.49
     Voj
    0.48
     коюмдары
    0.48
    STRA
    0.48
     své
    0.48
     počas
    0.48
     enz
    0.47
     كبير
    0.46
     الحديد
    0.46
    Act Density 0.000%

    No Known Activations