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

    Neuronpedia

    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash

    This neuron activates on the “Eleventh Circuit” label (the ordinal “-th” in “Eleventh Circuit”) in court case headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    4
    -0.07
     tjejer
    -0.06
    ’Brien
    -0.06
     harmful
    -0.06
    anol
    -0.06
     Sonia
    -0.06
     Approval
    -0.06
    =>{↵
    -0.06
    ;;↵↵
    -0.06
    очь
    -0.06
    POSITIVE LOGITS
    inaire
    0.07
     روم
    0.06
     deix
    0.06
    ubern
    0.06
     UIFont
    0.06
     Cursors
    0.06
     nymph
    0.06
    �
    0.06
     ولم
    0.06
     Tome
    0.06
    Act Density 0.000%

    No Known Activations