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

    Neuronpedia

    INDEX
    Explanations

    traps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Đáp
    0.44
    itate
    0.42
    ئی
    0.42
    ii
    0.41
    poner
    0.40
     quiser
    0.40
    duc
    0.39
    aron
    0.39
     Kiểm
    0.39
    ific
    0.39
    POSITIVE LOGITS
    л
    0.55
    на
    0.54
    fprintf
    0.54
     mites
    0.51
     eutectic
    0.50
    阱
    0.49
     mite
    0.49
    ียม
    0.48
     pitfalls
    0.48
     generalised
    0.48
    Act Density 0.005%

    No Known Activations