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

    Neuronpedia

    INDEX
    Explanations

    quantization and angles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.56
     Toyota
    0.46
     Toutes
    0.45
     Surat
    0.44
    يًا
    0.44
     Chevrolet
    0.44
     tutte
    0.42
    жета
    0.42
     suppressor
    0.42
     Motorola
    0.42
    POSITIVE LOGITS
    ap
    0.55
    ain
    0.51
     spain
    0.49
    ोक
    0.48
    B
    0.48
     lije
    0.47
    headlines
    0.47
    lare
    0.47
    /*',
    0.47
     اﻻ
    0.46
    Act Density 0.002%

    No Known Activations