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

    Neuronpedia

    INDEX
    Explanations

    postcodes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mmmm
    0.53
    1
    0.52
    soever
    0.50
     titanium
    0.49
    ª
    0.48
    Implementation
    0.47
    ttes
    0.47
     Taiwan
    0.47
     Implementation
    0.47
     Leben
    0.46
    POSITIVE LOGITS
    ا
    0.71
    و
    0.59
    en
    0.57
    на
    0.56
    ﻦ
    0.55
    א
    0.55
    先行
    0.54
    ন
    0.54
    ن
    0.54
    お
    0.53
    Act Density 0.003%

    No Known Activations