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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     biological
    -0.07
     summarizes
    -0.07
     possess
    -0.07
     tooltips
    -0.07
    ologies
    -0.06
     mole
    -0.06
    +w
    -0.06
    榜
    -0.06
    songs
    -0.06
     ترجمه
    -0.06
    POSITIVE LOGITS
    -‐
    0.06
    少年
    0.06
     Lib
    0.06
    执行
    0.06
    _EXEC
    0.06
    BJECT
    0.06
    ι
    0.06
    ौल
    0.06
     IPV
    0.06
    pile
    0.06
    Act Density 0.029%

    No Known Activations