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

    Neuronpedia

    INDEX
    Explanations

    good lighting quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <sup>
    0.34
    да
    0.34
    ‹
    0.33
    EN
    0.31
     <
    0.30
    ாய
    0.30
    зи
    0.30
    ﻃ
    0.30
    тов
    0.29
    gebra
    0.29
    POSITIVE LOGITS
    al
    0.49
    ll
    0.40
     analyser
    0.39
    d
    0.39
    enting
    0.38
     compliqué
    0.37
     succes
    0.37
    Después
    0.36
     nặng
    0.36
    ด
    0.36
    Act Density 0.000%

    No Known Activations