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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash

    The neuron activates on individual personal names (proper names) in legal text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _OVERFLOW
    -0.07
    anol
    -0.07
     craw
    -0.07
     inquiry
    -0.07
    mel
    -0.07
     squat
    -0.07
    ición
    -0.07
     Format
    -0.06
    _cmds
    -0.06
    ,count
    -0.06
    POSITIVE LOGITS
    "};
↵
    0.06
    ように
    0.06
    >");
↵
    0.06
    )");
↵
    0.06
    $product
    0.06
     Responsive
    0.06
     Md
    0.06
     "#
    0.06
    essor
    0.06
    _GT
    0.06
    Act Density 0.016%

    No Known Activations