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

    Neuronpedia

    INDEX
    Explanations

    commercial tech

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     activité
    0.67
    ẃ
    0.60
     ફાય
    0.57
    کور
    0.56
    ਵ
    0.55
    抂
    0.55
    ంబేద్
    0.54
    benef
    0.54
    spedes
    0.54
     augmenté
    0.54
    POSITIVE LOGITS
    riak
    0.61
     Rag
    0.60
    aka
    0.57
     RG
    0.57
     Mitch
    0.56
    ถึง
    0.55
     bisher
    0.55
     Nemat
    0.54
     Thousand
    0.54
    ariyam
    0.53
    Act Density 0.000%

    No Known Activations