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

    Neuronpedia

    INDEX
    Explanations

    withstanding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puberty
    -0.08
    疾病的
    -0.07
    𝑼
    -0.07
    -one
    -0.07
    BIN
    -0.07
    ﭺ
    -0.07
    重整
    -0.07
     răng
    -0.07
    Clinical
    -0.07
    做的
    -0.07
    POSITIVE LOGITS
    �
    0.07
    standing
    0.07
     impres
    0.06
    تأ
    0.06
    .monitor
    0.06
    もっと
    0.06
     asteroid
    0.06
     convers
    0.06
    _remain
    0.06
     jemand
    0.06
    Act Density 0.001%

    No Known Activations