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

    Neuronpedia

    INDEX
    Explanations

    constraints for text generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    notlocked
    0.29
     estere
    0.29
    clientsdetails
    0.28
     unsolicited
    0.27
     operands
    0.27
     valet
    0.26
     formality
    0.26
     differentiates
    0.26
     mediocr
    0.25
     vérité
    0.25
    POSITIVE LOGITS
    A
    0.41
    I
    0.40
    O
    0.40
     レ
    0.38
    K
    0.38
    C
    0.38
    R
    0.38
    र
    0.37
    T
    0.37
    J
    0.37
    Act Density 0.002%

    No Known Activations