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

    Neuronpedia

    INDEX
    Explanations

    rest

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens and adjacent measurement or count expressions, i.e. it detects numbers and quantities in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     affinity
    -0.07
    �어
    -0.07
     newX
    -0.07
    _tax
    -0.07
    _sprite
    -0.07
    件
    -0.06
     Gould
    -0.06
     thickness
    -0.06
    dera
    -0.06
     burdens
    -0.06
    POSITIVE LOGITS
     mi
    0.07
    첨부
    0.06
     looking
    0.06
     UPDATED
    0.06
    ont
    0.06
     proti
    0.06
    _ud
    0.06
    -enabled
    0.06
    -ro
    0.06
    [image
    0.06
    Act Density 0.096%

    No Known Activations