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

    Neuronpedia

    INDEX
    Explanations

    evaluating potential and teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     encouraged
    0.46
     있으
    0.43
     осуществляется
    0.39
     simbol
    0.39
     inextric
    0.39
     debug
    0.39
     unen
    0.39
     имеются
    0.39
     debes
    0.38
    ‌.
    0.38
    POSITIVE LOGITS
    full
    0.48
    quality
    0.45
    ي
    0.45
    interpol
    0.44
    free
    0.43
    rew
    0.42
    centaje
    0.42
    length
    0.41
    ration
    0.41
     AWD
    0.41
    Act Density 0.000%

    No Known Activations