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

    Neuronpedia

    INDEX
    Explanations

    behind many

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FORM
    0.55
    खबर
    0.48
    will
    0.47
    চৈতন্যের
    0.46
    క్ర
    0.44
    Scenic
    0.44
    urm
    0.44
    Finance
    0.43
    market
    0.43
    वित्त
    0.43
    POSITIVE LOGITS
     caja
    0.47
     كبيرة
    0.45
    指揮
    0.44
    inä
    0.44
     Некоторые
    0.43
     بخشی
    0.43
     冖
    0.42
     дея
    0.42
     tolerable
    0.42
     pareja
    0.42
    Act Density 0.001%

    No Known Activations