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

    Neuronpedia

    INDEX
    Explanations

    hyphen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ảo
    -0.08
    ỡ
    -0.07
    (pkt
    -0.07
    jabi
    -0.07
    slashes
    -0.07
    .removeFrom
    -0.07
     evangelical
    -0.07
    öyle
    -0.07
    أور
    -0.07
     مؤ
    -0.07
    POSITIVE LOGITS
    做的
    0.07
    (",
    0.07
    "]↵
    0.07
    每天
    0.07
     """
↵
    0.07
    弘扬
    0.07
     clone
    0.07
    对待
    0.07
    {/*
    0.07
     Decor
    0.07
    Act Density 0.008%

    No Known Activations