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

    Neuronpedia

    INDEX
    Explanations

    Writing/defining content

    np_max-act · gemini-2.0-flash

    The neuron detects when the text is talking about using or including numeric metrics (percentages, figures, counts) to quantify achievements—especially in the context of resume or CV entries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (Convert
    -0.07
    ster
    -0.07
     через
    -0.06
    _finish
    -0.06
    Contin
    -0.06
    記
    -0.06
    _RETURNTRANSFER
    -0.06
    \xf
    -0.06
    >Lorem
    -0.06
    .do
    -0.06
    POSITIVE LOGITS
     newly
    0.07
     rightful
    0.07
    ocyte
    0.06
     şekil
    0.06
     Minor
    0.06
    LIGHT
    0.06
     overwhelming
    0.06
    cour
    0.06
     inbox
    0.06
     Kind
    0.06
    Act Density 0.068%

    No Known Activations