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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric tokens and quantitative data (e.g. dates, measurements, statistics).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     intervene
    -0.06
     JScrollPane
    -0.06
    .toFloat
    -0.06
    stantiate
    -0.06
     frog
    -0.06
     subdiv
    -0.06
    _fg
    -0.06
     Feed
    -0.06
     �
    -0.06
    Skip
    -0.06
    POSITIVE LOGITS
    getError
    0.07
     провер
    0.07
    Mass
    0.06
    arged
    0.06
    Algorithm
    0.06
    かし
    0.06
    aniu
    0.06
    ?>"></
    0.06
    ecause
    0.05
    oenix
    0.05
    Act Density 0.045%

    No Known Activations