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

    Neuronpedia

    INDEX
    Explanations

    F

    np_max-act · gemini-2.0-flash

    This neuron activates on the decimal portions of legal reporter citations (e.g. the “.2​68359375” in “F.2​68359375d”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ERY
    -0.06
     incremented
    -0.06
     Initialization
    -0.06
    .publish
    -0.06
    animation
    -0.06
     زیادی
    -0.06
    _trees
    -0.06
     muchas
    -0.06
     borderSide
    -0.06
     skip
    -0.06
    POSITIVE LOGITS
     Cele
    0.07
     срок
    0.07
    rp
    0.07
    pecia
    0.06
    思
    0.06
     THEN
    0.06
     희
    0.06
    Tuple
    0.06
     NOAA
    0.06
    ्त
    0.06
    Act Density 0.001%

    No Known Activations