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

    Neuronpedia

    INDEX
    Explanations

    mathematics

    np_max-act · gemini-2.0-flash

    The neuron activates on specialized mathematical terminology—particularly names of branches or topics like “geometry,” “algebra,” “theory,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Minimal
    -0.07
     rules
    -0.07
    iable
    -0.07
    ілі
    -0.07
     lesions
    -0.07
    says
    -0.06
     maintained
    -0.06
     Jacqu
    -0.06
    _apply
    -0.06
    aro
    -0.06
    POSITIVE LOGITS
    .quality
    0.07
    .CreateCommand
    0.07
    GU
    0.06
    νού
    0.06
    tej
    0.06
     καν
    0.06
     kuzey
    0.06
     konci
    0.06
    Caller
    0.06
     Ủy
    0.06
    Act Density 0.040%

    No Known Activations