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

    Neuronpedia

    INDEX
    Explanations

    Code/Errors

    np_max-act · gemini-2.0-flash

    This neuron detects tokens from programming stack traces or code references—specifically file/path names and extensions (e.g. “Menu.exe”, “.c”, “android.view.LayoutInflater.java”) and related line‐number or memory‐address tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    官
    -0.06
    _segments
    -0.06
    _RST
    -0.06
    (substr
    -0.06
    /fa
    -0.06
    .business
    -0.06
     мас
    -0.06
    .r
    -0.06
     verifier
    -0.06
     YOU
    -0.06
    POSITIVE LOGITS
    ÄŸ
    0.07
     ImGui
    0.06
     swings
    0.06
     comforts
    0.06
    Clin
    0.06
    ;element
    0.06
    ��
    0.06
    .Enter
    0.06
    -east
    0.06
    σκεται
    0.06
    Act Density 0.038%

    No Known Activations