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

    Neuronpedia

    INDEX
    Explanations

    lists and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ideology
    0.50
     проце
    0.50
     organizacional
    0.48
    ться
    0.48
    できない
    0.47
    電流
    0.47
    創造
    0.43
    อต
    0.43
    度の
    0.42
     immisc
    0.42
    POSITIVE LOGITS
    S
    0.56
    J
    0.50
    ing
    0.48
    ished
    0.47
     vorhand
    0.45
    ogram
    0.45
    ular
    0.45
    essed
    0.44
    ushed
    0.44
    ita
    0.44
    Act Density 0.002%

    No Known Activations