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

    Neuronpedia

    INDEX
    Explanations

    Clement and Clementine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Straight
    0.40
     straight
    0.39
    直线
    0.39
     wcześ
    0.38
    lomer
    0.38
     STRAIGHT
    0.38
     spray
    0.37
     códigos
    0.37
    Straight
    0.37
    축
    0.37
    POSITIVE LOGITS
     Clement
    0.78
    clementine
    0.68
     Clem
    0.65
     cle
    0.64
     кле
    0.63
     Clément
    0.57
    Cle
    0.57
     Clements
    0.55
     Clemens
    0.55
    cle
    0.53
    Act Density 0.002%

    No Known Activations