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

    Neuronpedia

    INDEX
    Explanations

    organizational links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     detoxification
    0.81
     precipitation
    0.77
     psychiatric
    0.76
     tubing
    0.75
     নিঃস
    0.72
    ibald
    0.72
     प्रकोष्ठ
    0.71
    రిత్ర
    0.71
     кле
    0.71
    precipitation
    0.70
    POSITIVE LOGITS
     learnt
    0.86
     wondering
    0.85
    祎
    0.80
    মর
    0.78
    想不到
    0.78
    rać
    0.78
    Illust
    0.77
     wondered
    0.77
    拉
    0.76
     भास्कर
    0.76
    Act Density 0.033%

    No Known Activations