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

    Neuronpedia

    INDEX
    Explanations

    crime/legal proceedings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \AppData
    -0.08
    ǐ
    -0.07
     Despite
    -0.07
     Sanford
    -0.06
     tote
    -0.06
    KD
    -0.06
    Despite
    -0.06
    .startTime
    -0.06
     muttered
    -0.06
     overweight
    -0.06
    POSITIVE LOGITS
     excited
    0.06
     exterior
    0.06
    .getTitle
    0.06
    lassian
    0.06
     гриб
    0.06
    (found
    0.06
     rhe
    0.06
    /lab
    0.06
     нек
    0.06
     zvol
    0.05
    Act Density 0.013%

    No Known Activations