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

    Neuronpedia

    INDEX
    Explanations

    paste

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .receiver
    -0.07
    嫌
    -0.07
     гід
    -0.07
    岁
    -0.06
     obrig
    -0.06
     lows
    -0.06
     regress
    -0.06
    456
    -0.06
     Creator
    -0.06
     ssize
    -0.06
    POSITIVE LOGITS
     pasta
    0.08
     кус
    0.08
    esc
    0.08
    Past
    0.08
    Paste
    0.07
     Pasta
    0.07
     â
    0.07
    â
    0.07
    ESC
    0.07
     pastor
    0.07
    Act Density 0.014%

    No Known Activations