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

    Neuronpedia

    INDEX
    Explanations

    function or purpose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மற்றும்
    0.70
     அல்லது
    0.66
     tambah
    0.66
     yoki
    0.64
     YOU
    0.64
    happiness
    0.64
     atau
    0.63
     hoặc
    0.62
     exatamente
    0.62
     یا
    0.61
    POSITIVE LOGITS
    用于
    0.86
     用于
    0.82
    用途
    0.76
     použití
    0.75
     penggunaan
    0.74
     uses
    0.74
    用於
    0.74
    สำหรับการ
    0.73
     Uses
    0.73
     kullanım
    0.72
    Act Density 0.298%

    No Known Activations