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

    Neuronpedia

    INDEX
    Explanations

    Chemistry elements

    np_max-act · gemini-2.0-flash

    This neuron detects chemical element symbols (especially metal abbreviations) in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    itone
    -0.07
    -suite
    -0.06
    _ATTACH
    -0.06
    सत
    -0.06
     undergoing
    -0.06
    erno
    -0.06
    atte
    -0.06
    ụ
    -0.06
     ч
    -0.06
    igu
    -0.06
    POSITIVE LOGITS
    Sales
    0.07
    ampilkan
    0.06
    νοι
    0.06
     John
    0.06
    Tabs
    0.06
     Jenny
    0.06
    Sphere
    0.06
     Zoom
    0.06
    John
    0.06
     Teams
    0.06
    Act Density 0.007%

    No Known Activations