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

    Neuronpedia

    INDEX
    Explanations

    signs and unusual things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Environment
    -0.07
    _records
    -0.07
    走势
    -0.07
    icmp
    -0.06
    .dict
    -0.06
    被骗
    -0.06
    .radius
    -0.06
    ember
    -0.06
    .square
    -0.06
    _TOUCH
    -0.06
    POSITIVE LOGITS
     phones
    0.07
    拱
    0.07
     directional
    0.07
     Orchestra
    0.07
     roofing
    0.07
    ちゃんと
    0.07
     ")";↵
    0.07
    cop
    0.07
    انتخاب
    0.07
    重返
    0.06
    Act Density 0.056%

    No Known Activations