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

    Neuronpedia

    INDEX
    Explanations

    rate of change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Annotation
    0.41
    Maximum
    0.40
     pourcentage
    0.39
    भारतीय
    0.38
     Chrom
    0.37
    ivalent
    0.36
    robin
    0.36
     échantillons
    0.36
    Annotations
    0.36
    ESSAGE
    0.36
    POSITIVE LOGITS
    短暂
    0.40
     stiffness
    0.39
     pari
    0.39
     yay
    0.39
     👇
    0.38
     mb
    0.37
     स्त
    0.37
     газе
    0.37
     酒
    0.37
     😊
    0.37
    Act Density 0.000%

    No Known Activations