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

    Neuronpedia

    INDEX
    Explanations

    counting variables and loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ar
    0.47
    Há
    0.46
     výro
    0.45
    یه
    0.45
    英語版
    0.44
     явля
    0.43
    ambiental
    0.43
    bmatrix
    0.42
    徴
    0.42
    haired
    0.41
    POSITIVE LOGITS
    𝐦
    0.55
    𝐕
    0.55
     outsourcing
    0.54
    𝐅
    0.54
     irrigation
    0.53
    𝐒
    0.51
     (−
    0.50
    落实
    0.50
    𝐮
    0.49
     numerator
    0.49
    Act Density 0.020%

    No Known Activations