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

    Neuronpedia

    INDEX
    Explanations

    distance units

    np_max-act · gemini-2.0-flash

    This neuron activates on decimal numbers (floating‐point values), especially measurements like “0.96923828125” or “2.890625.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     IC
    -0.07
    _RSP
    -0.07
     implicit
    -0.06
     {'
    -0.06
     oven
    -0.06
    mart
    -0.06
     Eph
    -0.06
     Shaman
    -0.06
    /email
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    -cols
    0.07
     Manning
    0.07
    -clear
    0.07
     worsening
    0.07
     يق
    0.06
    _flat
    0.06
    appearance
    0.06
    reopen
    0.06
    ancellor
    0.06
     рег
    0.06
    Act Density 0.007%

    No Known Activations