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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SHARE
    -0.07
    .Nome
    -0.07
     vrch
    -0.06
     ､
    -0.06
    427
    -0.06
    uter
    -0.06
     zm
    -0.06
    SAM
    -0.06
    [F
    -0.06
     pg
    -0.06
    POSITIVE LOGITS
    size
    0.07
    translated
    0.06
    otechnology
    0.06
     Měst
    0.06
    otechn
    0.06
    -offset
    0.06
    906
    0.06
    (($
    0.06
    ẻ
    0.06
    ！");↵
    0.06
    Act Density 0.010%

    No Known Activations