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

    Neuronpedia

    INDEX
    Explanations

    common english words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IENCE
    -0.07
    Study
    -0.07
    $a
    -0.06
     cram
    -0.06
     bears
    -0.06
    dates
    -0.06
    AW
    -0.06
    面积
    -0.06
     study
    -0.06
    _positions
    -0.06
    POSITIVE LOGITS
    INGTON
    0.07
     clubhouse
    0.06
    /plain
    0.06
    청
    0.06
     connectionString
    0.06
     finest
    0.06
    oglobin
    0.06
     Snapdragon
    0.06
    コン
    0.06
    (bottom
    0.06
    Act Density 0.000%

    No Known Activations