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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    The neuron detects floating‐point numeric values (decimal numbers) used as scientific parameter measurements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Marcus
    -0.07
    ugh
    -0.07
    ुमत
    -0.06
    @endforeach
    -0.06
    oubles
    -0.06
    .Sockets
    -0.06
    Marcus
    -0.06
    brown
    -0.06
    QualifiedName
    -0.06
     Virus
    -0.06
    POSITIVE LOGITS
     Se
    0.06
    ublice
    0.06
     Rd
    0.06
    ião
    0.06
     değiş
    0.06
    (fd
    0.06
     programu
    0.06
     discard
    0.06
    ुब
    0.06
    番
    0.06
    Act Density 0.054%

    No Known Activations