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

    Neuronpedia

    INDEX
    Explanations

    digital marketing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    扣
    0.68
    Journey
    0.66
     weight
    0.66
    分类
    0.65
     Multiply
    0.65
     βασ
    0.65
    दिया
    0.64
     Weight
    0.64
     Journey
    0.64
    𝕞
    0.63
    POSITIVE LOGITS
    ంతరం
    0.72
    õi
    0.66
    ങ്ങളെ
    0.65
     звер
    0.65
    ozz
    0.64
    ពេល
    0.64
    aphore
    0.63
     rationalize
    0.61
     kill
    0.60
    Handle
    0.60
    Act Density 0.046%

    No Known Activations