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

    Neuronpedia

    INDEX
    Explanations

    may

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     win
    -0.07
    }-{
    -0.07
    Interfaces
    -0.07
    awei
    -0.07
    研
    -0.07
     kinds
    -0.06
     policing
    -0.06
    nat
    -0.06
     Rif
    -0.06
    mlin
    -0.06
    POSITIVE LOGITS
     –↵↵
    0.07
    .swing
    0.06
    '",↵
    0.06
     Schumer
    0.06
     scrutiny
    0.06
     scrutin
    0.06
     широк
    0.06
     χρησιμοποι
    0.06
    ichern
    0.06
     tq
    0.06
    Act Density 0.080%

    No Known Activations