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

    Neuronpedia

    INDEX
    Explanations

    detailed explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Few
    1.23
     понадоби
    1.22
    জ
    1.20
     রেখেছেন
    1.19
    브
    1.18
    फारिश
    1.18
     admires
    1.17
    þ
    1.14
    高
    1.12
    พ
    1.11
    POSITIVE LOGITS
    s
    1.56
    ات
    1.50
    样子
    1.22
    Oj
    1.20
    र्देश
    1.18
     gemäß
    1.15
    ે
    1.13
    ς
    1.11
     dump
    1.09
    nesday
    1.09
    Act Density 0.000%

    No Known Activations