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

    Neuronpedia

    INDEX
    Explanations

    ® or ™ followed by product/feature names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    0.47
    ీ
    0.45
    ah
    0.45
    it
    0.45
    قیع
    0.43
    ${
    0.42
    pg
    0.42
    ा
    0.41
    śmy
    0.40
    型
    0.39
    POSITIVE LOGITS
     underwear
    0.54
    т
    0.53
     installments
    0.51
    ngModel
    0.51
     ape
    0.50
     erotic
    0.50
    setOn
    0.50
    ోంది
    0.50
     anus
    0.50
    ካከል
    0.49
    Act Density 0.008%

    No Known Activations