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

    Neuronpedia

    INDEX
    Explanations

    code and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вався
    0.41
     attendant
    0.40
    }$')
    0.40
    lements
    0.39
    🧿
    0.39
    ときに
    0.38
    lectual
    0.38
    უნ
    0.38
    +')
    0.36
    ']))
    0.36
    POSITIVE LOGITS
     發
    0.48
     HUOBI
    0.44
     CtApp
    0.43
     प्रदर्शन
    0.43
    σης
    0.42
     對
    0.42
     био
    0.42
     Fonbet
    0.41
     όπως
    0.41
     Trên
    0.41
    Act Density 0.063%

    No Known Activations