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

    Neuronpedia

    INDEX
    Explanations

    Code/Copyright

    np_max-act · gemini-2.0-flash

    The neuron specifically activates on floating‐point number literals (e.g. “3.140625,” “0.3779296875,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    (opts
    -0.07
    ','".$
    -0.07
    (errorMessage
    -0.06
     flagship
    -0.06
     TextView
    -0.06
    ML
    -0.06
     BAD
    -0.06
     ermög
    -0.06
     bad
    -0.06
     GR
    -0.06
    POSITIVE LOGITS
     область
    0.06
    _MORE
    0.06
     provoked
    0.06
    інь
    0.06
     Form
    0.06
     ''}↵
    0.06
     σει
    0.06
     }}"↵
    0.06
     trespass
    0.06
     Critics
    0.06
    Act Density 0.001%

    No Known Activations