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

    Neuronpedia

    INDEX
    Explanations

    music

    np_max-act · gemini-2.0-flash

    The neuron fires on sequences of capitalized words and numbers inside quotation marks—i.e. song or track titles.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Mit
    -0.06
    Early
    -0.06
     }↵
    -0.06
    Alarm
    -0.06
    ^\
    -0.06
    542
    -0.06
    Alexander
    -0.06
    }</
    -0.06
    Lean
    -0.06
     })↵↵
    -0.06
    POSITIVE LOGITS
    _SUM
    0.07
     vibe
    0.07
     undergo
    0.07
     fostering
    0.06
    _holder
    0.06
     instituted
    0.06
     cite
    0.06
    .std
    0.06
     السعودية
    0.06
     вариант
    0.06
    Act Density 0.028%

    No Known Activations