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

    Neuronpedia

    INDEX
    Explanations

    model system

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HttpException
    -0.07
    сер
    -0.06
    enie
    -0.06
     Ninth
    -0.06
     záp
    -0.06
    esda
    -0.06
    iể
    -0.06
    .Col
    -0.06
    نب
    -0.06
    舰
    -0.06
    POSITIVE LOGITS
    "She
    0.06
    	gl
    0.06
     jPanel
    0.06
    ?>↵↵↵
    0.06
    grade
    0.06
     fishing
    0.06
    „N
    0.05
    “She
    0.05
    $$
    0.05
    rop
    0.05
    Act Density 0.018%

    No Known Activations