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

    Neuronpedia

    INDEX
    Explanations

    requirement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     b
    -0.07
     ro
    -0.06
    ()},↵
    -0.06
    {}]
    -0.06
     readability
    -0.06
     시간
    -0.06
    lyn
    -0.06
     děti
    -0.06
     fo
    -0.06
     treaties
    -0.06
    POSITIVE LOGITS
     giản
    0.07
     potřeb
    0.07
    Avg
    0.06
    acic
    0.06
     ש
    0.06
     AudioManager
    0.06
    angered
    0.06
    طل
    0.06
    剣
    0.06
    .ordinal
    0.06
    Act Density 0.235%

    No Known Activations