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

    Neuronpedia

    INDEX
    Explanations

    build, until, continue, evade, sustainable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ı
    0.59
     ಕಾ
    0.49
     Щ
    0.47
    ategorie
    0.46
    i
    0.45
    সম্পাদক
    0.44
    रज
    0.44
    KS
    0.44
    ack
    0.43
     Accordingly
    0.43
    POSITIVE LOGITS
    وە
    0.52
    ای
    0.49
     defrost
    0.49
    गरण
    0.47
    腧
    0.46
    خانه
    0.43
    tired
    0.43
     charismatic
    0.43
    tyard
    0.42
    密钥
    0.42
    Act Density 0.001%

    No Known Activations