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

    Neuronpedia

    INDEX
    Explanations

    Need, want, like

    np_max-act · gemini-2.0-flash

    The neuron fires on phrases describing requests to develop software applications (especially “code,” “mobile,” “application,” “project,” “develop,” “need,” “simple”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _bus
    -0.06
     strokes
    -0.06
    αιο
    -0.06
     ANSI
    -0.06
    Improved
    -0.06
     på
    -0.06
    atrigesimal
    -0.06
     oltre
    -0.06
    ä
    -0.06
    -yyyy
    -0.06
    POSITIVE LOGITS
    ('%
    0.07
     decl
    0.07
     compreh
    0.07
     병
    0.07
     grounds
    0.06
     Arabs
    0.06
     Stef
    0.06
     обеспеч
    0.06
     Original
    0.06
    (Target
    0.06
    Act Density 0.024%

    No Known Activations