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

    Neuronpedia

    INDEX
    Explanations

    default

    np_max-act · gemini-2.0-flash

    The neuron is triggered by decimal numbers (floating‐point values).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     EnumerableStream
    -0.07
     conduc
    -0.06
    _ISS
    -0.06
     tre
    -0.06
    méně
    -0.06
     verbess
    -0.06
     тр
    -0.06
    vrd
    -0.06
    329
    -0.06
    	DD
    -0.06
    POSITIVE LOGITS
     Mickey
    0.08
    .spacing
    0.07
     Decay
    0.07
     padr
    0.06
    attrs
    0.06
    fillna
    0.06
     свид
    0.06
    Flexible
    0.06
    .onclick
    0.06
    एम
    0.06
    Act Density 0.007%

    No Known Activations