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

    Neuronpedia

    INDEX
    Explanations

    Units

    np_max-act · gemini-2.0-flash

    The neuron responds to numeric values—especially decimal numbers—in the text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     uprising
    -0.07
     caliber
    -0.07
     obsc
    -0.07
     PARTIC
    -0.07
     StartCoroutine
    -0.07
     ClassNotFoundException
    -0.07
    �
    -0.06
    ／／／／
    -0.06
    (MPI
    -0.06
    mouseout
    -0.06
    POSITIVE LOGITS
     бед
    0.07
     код
    0.07
     Tub
    0.07
    .Area
    0.07
    [w
    0.06
    gricult
    0.06
    金额
    0.06
     autism
    0.06
     ajust
    0.06
     bonuses
    0.06
    Act Density 0.000%

    No Known Activations