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

    Neuronpedia

    INDEX
    Explanations

    knows where

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ERICK
    0.48
     छि
    0.48
     해결
    0.47
     Inequality
    0.45
     ዓይ
    0.45
     모습을
    0.44
     drunkenness
    0.44
    spolit
    0.43
     Shamrock
    0.43
     Holt
    0.43
    POSITIVE LOGITS
     points
    0.49
    一般
    0.48
     યાદ
    0.48
    طة
    0.47
    genza
    0.46
    椅子
    0.46
    酒店
    0.46
    بال
    0.45
    称
    0.45
    بالإنجليزية
    0.44
    Act Density 0.000%

    No Known Activations