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

    Neuronpedia

    INDEX
    Explanations

    cancel

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of noise-cancellation or related terms (e.g. “noise-canceling,” “ANC,” blocking sounds).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _CHAT
    -0.07
     keyboardType
    -0.07
    (pDX
    -0.07
     LIABLE
    -0.06
    ».↵↵
    -0.06
    singleton
    -0.06
     sağlay
    -0.06
     بیر
    -0.06
     Patt
    -0.06
     generar
    -0.06
    POSITIVE LOGITS
     defenses
    0.07
     Jazz
    0.07
     accents
    0.06
     launches
    0.06
    년
    0.06
     raw
    0.06
     editing
    0.06
     nc
    0.06
    SqlCommand
    0.06
     清
    0.06
    Act Density 0.007%

    No Known Activations