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

    Neuronpedia

    INDEX
    Explanations

    includes a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    0.56
    i
    0.54
     Cran
    0.51
    h
    0.50
    bru
    0.48
    x
    0.46
     Chase
    0.45
     Ew
    0.45
     Arroyo
    0.45
    ew
    0.45
    POSITIVE LOGITS
     vendo
    0.55
     سی
    0.51
     நீரில்
    0.51
     forested
    0.50
     dónde
    0.47
    excited
    0.47
     போதும்
    0.47
     জানিয়ে
    0.47
     disple
    0.46
    ното
    0.46
    Act Density 0.000%

    No Known Activations