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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     listOf
    -0.07
    ADF
    -0.07
     sigma
    -0.07
     consumer
    -0.07
    ulatory
    -0.07
    .W
    -0.07
    adaptive
    -0.06
    υ
    -0.06
    랰
    -0.06
    Bay
    -0.06
    POSITIVE LOGITS
     kişi
    0.08
     máquina
    0.07
    ất
    0.07
    孤立
    0.07
    漆
    0.07
    خط
    0.07
    つき
    0.07
     trem
    0.07
    时间内
    0.07
    -net
    0.06
    Act Density 0.003%

    No Known Activations