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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    0.64
     c
    0.54
    ter
    0.53
    cr
    0.48
    inf
    0.46
    fer
    0.46
    ｃ
    0.46
    cl
    0.46
    bl
    0.45
    gr
    0.45
    POSITIVE LOGITS
    preprocessing
    0.38
    akur
    0.38
    Desired
    0.36
     forcible
    0.35
     proclaimed
    0.35
    Allocation
    0.35
    arello
    0.35
    脚
    0.35
    ARTS
    0.34
    iação
    0.34
    Act Density 0.077%

    No Known Activations