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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Surface
    -0.08
    atomic
    -0.07
     Apprentice
    -0.06
    ivariate
    -0.06
     sunlight
    -0.06
     ม
    -0.06
    credible
    -0.06
     tray
    -0.06
    elastic
    -0.06
    adí
    -0.06
    POSITIVE LOGITS
     pstmt
    0.06
    instruction
    0.06
    .setId
    0.06
    SuppressWarnings
    0.06
    .dest
    0.06
    .math
    0.05
    .rstrip
    0.05
    =line
    0.05
     ром
    0.05
    UGHT
    0.05
    Act Density 0.040%

    No Known Activations