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

    Neuronpedia

    INDEX
    Explanations

    any given, starting point

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Finally
    0.90
    介绍
    0.82
    Here
    0.81
    Ско
    0.80
    燧
    0.79
    Analyze
    0.79
    ílio
    0.79
    Эта
    0.76
    ঠে
    0.75
    उंट
    0.75
    POSITIVE LOGITS
     isomeric
    0.88
     deleterious
    0.80
     granulated
    0.76
     Стаўкі
    0.75
     Eropa
    0.74
    াধীন
    0.74
     옳은
    0.74
     могат
    0.73
    袷
    0.73
     ಎಂಬುದ
    0.71
    Act Density 0.086%

    No Known Activations