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

    Neuronpedia

    INDEX
    Explanations

    storage furniture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ح
    1.07
    Д
    0.74
    ien
    0.70
    rope
    0.68
     amply
    0.68
    dus
    0.67
     Есть
    0.65
    ның
    0.65
    ig
    0.64
    zą
    0.64
    POSITIVE LOGITS
     causar
    0.67
    湎
    0.67
     juu
    0.66
     bedside
    0.66
    ה
    0.65
    Estados
    0.65
    használ
    0.64
     Dahmer
    0.61
    ל
    0.61
    ﮭ
    0.61
    Act Density 0.082%

    No Known Activations