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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on numeric tokens (years, ages, decimal parts)—i.e. it detects numbers in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     validity
    -0.07
    ERAL
    -0.07
     HuffPost
    -0.06
    ,default
    -0.06
     scoff
    -0.06
    iators
    -0.06
    >If
    -0.06
     GameController
    -0.06
     cheering
    -0.06
     begging
    -0.06
    POSITIVE LOGITS
     Addiction
    0.06
     陳
    0.06
    티
    0.06
    .wind
    0.06
     imprisonment
    0.06
     Drag
    0.06
    ьв
    0.06
     "</
    0.06
    _ERRORS
    0.06
    .deltaTime
    0.06
    Act Density 0.011%

    No Known Activations