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

    Neuronpedia

    INDEX
    Explanations

    code blocks returning values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ،
    0.45
     trophic
    0.35
     escul
    0.35
     carbur
    0.35
     ingrédients
    0.35
     agglut
    0.34
     adsorb
    0.34
     embry
    0.34
     cogeneration
    0.34
     myocytes
    0.34
    POSITIVE LOGITS
    if
    0.64
    return
    0.50
    is
    0.47
    //
    0.44
    os
    0.44
    let
    0.40
    ie
    0.39
    while
    0.39
    set
    0.39
    ul
    0.37
    Act Density 0.551%

    No Known Activations