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

    Neuronpedia

    INDEX
    Explanations

    his

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ีพ
    -0.07
     Yao
    -0.07
    ительное
    -0.06
    otto
    -0.06
    chg
    -0.06
     waitress
    -0.06
    杯
    -0.06
    継
    -0.06
    ませ
    -0.06
    hot
    -0.06
    POSITIVE LOGITS
    ทร
    0.07
     متن
    0.07
    xFFFFFFFF
    0.06
     Spears
    0.06
     importante
    0.06
    .Scanner
    0.06
    ,password
    0.06
     scissors
    0.06
     Created
    0.06
     Jacobs
    0.06
    Act Density 0.000%

    No Known Activations