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

    Neuronpedia

    INDEX
    Explanations

    programming tools and libraries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ijden
    0.43
    ᓯ
    0.42
     xâm
    0.42
    iscid
    0.41
     개
    0.40
    iguous
    0.40
     gevallen
    0.40
    orescent
    0.39
    $,
    0.39
    wort
    0.39
    POSITIVE LOGITS
     çalışmalar
    0.60
     نئے
    0.58
     புதிய
    0.57
     Managing
    0.56
     শুরু
    0.56
    に必要な
    0.55
     开始
    0.54
     workflow
    0.53
    楽しい
    0.53
     ಪ್ರಯತ್ನ
    0.53
    Act Density 0.001%

    No Known Activations