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

    Neuronpedia

    INDEX
    Explanations

    Known for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ulang
    1.19
    সি
    1.15
    1.12
     تشوف
    1.10
    Voor
    1.09
    ﺪ
    1.05
    1.05
    أة
    1.04
    Shader
    1.04
    ગર
    1.03
    POSITIVE LOGITS
    ledged
    1.81
    晓
    1.69
    悉
    1.61
    struck
    1.47
    สึก
    1.41
     intimately
    1.39
     pasti
    1.39
    曉
    1.32
    lege
    1.32
    产权
    1.26
    Act Density 0.154%

    No Known Activations