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

    Neuronpedia

    INDEX
    Explanations

    influence and effect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    note
    0.37
    load
    0.36
    较大的
    0.36
     پلا
    0.35
    adors
    0.35
    viewport
    0.35
    log
    0.35
     দখলে
    0.35
    wedge
    0.34
    varia
    0.34
    POSITIVE LOGITS
    సరం
    0.41
     carefree
    0.41
     ഇടപെ
    0.41
     vidé
    0.40
    hse
    0.39
     gpm
    0.39
     nearest
    0.39
    ⊹
    0.38
     réglementation
    0.38
    iccation
    0.38
    Act Density 0.000%

    No Known Activations