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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uplicated
    -0.07
     six
    -0.07
    /book
    -0.06
    rik
    -0.06
    pard
    -0.06
     производ
    -0.06
     positional
    -0.06
    erts
    -0.06
    connect
    -0.06
    ubre
    -0.06
    POSITIVE LOGITS
     INTERNAL
    0.07
     silly
    0.06
    });↵↵
    0.06
     cherry
    0.06
     ''){↵
    0.06
     ESV
    0.06
    xffffffff
    0.06
    /******/
    0.05
    كر
    0.05
    .panel
    0.05
    Act Density 0.197%

    No Known Activations