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

    Neuronpedia

    INDEX
    Explanations

    family resemblance

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on numeric tokens that specify ages or years.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Af
    -0.06
    _you
    -0.06
    Learning
    -0.06
     serviced
    -0.06
     ammunition
    -0.06
    GMT
    -0.06
    -way
    -0.06
    Mapping
    -0.06
     pentru
    -0.06
    gn
    -0.06
    POSITIVE LOGITS
    <Response
    0.07
     ceased
    0.07
     plainly
    0.07
    ΟΓ
    0.06
     Immediate
    0.06
    ocratic
    0.06
     except
    0.06
     περιοχή
    0.06
    @login
    0.06
    .linspace
    0.06
    Act Density 0.025%

    No Known Activations