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

    Neuronpedia

    INDEX
    Explanations

    .cpp

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of mining actions and tool‐related terms (like “mine” and “tool”) in the code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     prevents
    -0.07
     daughters
    -0.06
     computer
    -0.06
     ox
    -0.06
    SECTION
    -0.06
     raid
    -0.06
     sniper
    -0.06
    ment
    -0.06
    -work
    -0.06
    "What
    -0.06
    POSITIVE LOGITS
     poru
    0.07
     DISTRIBUT
    0.07
     लड
    0.07
     концентра
    0.07
    ánchez
    0.07
    expanded
    0.06
    arlar
    0.06
    lein
    0.06
    Literal
    0.06
     dashed
    0.06
    Act Density 0.487%

    No Known Activations