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

    Neuronpedia

    INDEX
    Explanations

    maps and mapping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᆫ
    0.75
    ۔
    0.73
    és
    0.72
    ut
    0.71
    ão
    0.68
     blemishes
    0.67
     marqués
    0.67
     regimens
    0.67
    umps
    0.65
     calific
    0.65
    POSITIVE LOGITS
    ו
    1.13
     Map
    0.96
     map
    0.95
    Map
    0.84
    地图
    0.83
     Maps
    0.80
    も
    0.79
    ל
    0.79
    u
    0.78
     maps
    0.75
    Act Density 0.019%

    No Known Activations