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 detects the “F.” token marking Federal Reporter citations (e.g. F.2d, F.3d, F. Supp.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    VID
    -0.07
    097
    -0.07
    sum
    -0.07
    ,application
    -0.06
     ownerId
    -0.06
     benchmarks
    -0.06
    řád
    -0.06
    csi
    -0.06
    (xx
    -0.06
     Shapiro
    -0.06
    POSITIVE LOGITS
     신규
    0.07
     fecha
    0.07
     jewish
    0.06
     desires
    0.06
    _cached
    0.06
    .decrypt
    0.06
    _wind
    0.06
     �
    0.06
     wisdom
    0.06
     republic
    0.06
    Act Density 0.001%

    No Known Activations