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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     варі
    -0.07
    culture
    -0.06
     Ernest
    -0.06
     Některá
    -0.06
    Spacer
    -0.06
     grapes
    -0.06
    WithMany
    -0.06
     dello
    -0.06
    전히
    -0.06
     multis
    -0.06
    POSITIVE LOGITS
     pictureBox
    0.08
    iß
    0.07
    نام
    0.06
    یدن
    0.06
    /result
    0.06
    CODE
    0.06
    âu
    0.06
     ali
    0.06
    oh
    0.06
     BOX
    0.06
    Act Density 0.358%

    No Known Activations