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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Variable
    -0.07
    몯
    -0.07
    أفل
    -0.07
    Argentina
    -0.07
     laughter
    -0.06
     بذلك
    -0.06
     Bott
    -0.06
    弟
    -0.06
    סביבה
    -0.06
     Francisco
    -0.06
    POSITIVE LOGITS
    Rot
    0.07
    وش
    0.07
    EC
    0.07
     young
    0.07
    흥
    0.07
    _RES
    0.07
    .'</
    0.07
    )new
    0.07
    =""><
    0.07
    -loading
    0.07
    Act Density 0.161%

    No Known Activations