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

    Neuronpedia

    INDEX
    Explanations

    dash

    np_max-act · gemini-2.0-flash

    This neuron fires on numeric tokens representing floating‐point values (decimal numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Replica
    -0.07
     NN
    -0.07
    UTE
    -0.07
    spm
    -0.07
    mpjes
    -0.06
     Downloads
    -0.06
     ),
    -0.06
     whales
    -0.06
    _raw
    -0.06
    езда
    -0.06
    POSITIVE LOGITS
     повер
    0.07
    (default
    0.07
    .ManyToManyField
    0.06
     Draft
    0.06
     socialist
    0.06
    ##↵↵
    0.06
     indicated
    0.06
    Portfolio
    0.06
    ו�
    0.06
     considering
    0.06
    Act Density 0.007%

    No Known Activations