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

    Neuronpedia

    INDEX
    Explanations

    knew their, potential for, familiar under

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ανο
    0.50
    探し
    0.49
     වශ
    0.46
    廿
    0.46
    透过
    0.45
    ကျော်
    0.45
    २
    0.45
    сцю
    0.45
    න්
    0.45
    三分
    0.45
    POSITIVE LOGITS
     vegetal
    0.45
     boje
    0.45
    Vars
    0.44
     Mysteries
    0.42
    فير
    0.41
    ("
    0.41
     painful
    0.40
    ти
    0.40
     tissue
    0.40
     poeta
    0.40
    Act Density 0.000%

    No Known Activations