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

    Neuronpedia

    INDEX
    Explanations

    H

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clipping
    -0.07
    唇
    -0.07
     Hoy
    -0.06
     algun
    -0.06
    edar
    -0.06
    tan
    -0.06
     College
    -0.06
    -mobile
    -0.06
    rror
    -0.06
    {}.
    -0.06
    POSITIVE LOGITS
    .stdin
    0.07
    .cwd
    0.07
    频次
    0.06
    .conv
    0.06
    ιβ
    0.06
     BOOST
    0.06
    START
    0.06
     σχε
    0.06
     intriguing
    0.06
     `;↵
    0.06
    Act Density 0.000%

    No Known Activations