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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kas
    -0.07
    operand
    -0.07
     Hash
    -0.07
    observ
    -0.07
     exacerb
    -0.06
     TableCell
    -0.06
    	task
    -0.06
    esc
    -0.06
    挲
    -0.06
    "Do
    -0.06
    POSITIVE LOGITS
     Archives
    0.08
     decrease
    0.07
    מוני
    0.07
     wannonce
    0.07
    줘
    0.06
    league
    0.06
     فقط
    0.06
    不断的
    0.06
    yyval
    0.06
    贡献力量
    0.06
    Act Density 0.000%

    No Known Activations