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

    Neuronpedia

    INDEX
    Explanations

    programming syntax, math expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agę
    0.43
    åd
    0.40
    嬗
    0.40
     Courtney
    0.40
    薷
    0.39
    getFocus
    0.38
    heen
    0.38
    gård
    0.38
     नितिन
    0.38
    كد
    0.38
    POSITIVE LOGITS
    r
    0.38
    )['
    0.36
    z
    0.35
    pas
    0.35
    Tag
    0.35
     compro
    0.34
     pas
    0.34
     prime
    0.34
    Z
    0.34
    CAT
    0.34
    Act Density 0.002%

    No Known Activations