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

    Neuronpedia

    INDEX
    Explanations

    illegal

    np_max-act · gemini-2.0-flash

    This neuron never produces a non-zero response—it doesn’t detect any pattern (i.e. it’s effectively “dead”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    FileSystem
    -0.06
    codec
    -0.06
    feel
    -0.06
    NECT
    -0.06
     Sunday
    -0.06
    Wake
    -0.06
     defs
    -0.06
     такие
    -0.06
    大小
    -0.06
     швид
    -0.06
    POSITIVE LOGITS
     brasile
    0.07
     destroyer
    0.07
     Judge
    0.07
     WOM
    0.07
    atown
    0.06
    ucking
    0.06
    ologi
    0.06
    <Unit
    0.06
     rant
    0.06
    .setDate
    0.06
    Act Density 0.053%

    No Known Activations