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

    Neuronpedia

    INDEX
    Explanations

    crypto markets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     abrang
    0.75
     gồm
    0.68
     לפי
    0.67
    loff
    0.66
    동안
    0.66
     lakes
    0.66
    時点
    0.66
     lake
    0.65
     outages
    0.65
     Несмотря
    0.65
    POSITIVE LOGITS
    ше
    0.79
    ah
    0.75
    ем
    0.75
    z
    0.75
    ز
    0.73
    ウ
    0.73
    ва
    0.73
    es
    0.72
    ας
    0.72
     favorites
    0.71
    Act Density 0.000%

    No Known Activations