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

    Neuronpedia

    INDEX
    Explanations

    years

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    각
    -0.07
     ред
    -0.06
    achine
    -0.06
     UDP
    -0.06
     πρό
    -0.06
    爵
    -0.06
     경우
    -0.06
    χω
    -0.06
     ning
    -0.06
    uvre
    -0.06
    POSITIVE LOGITS
     unexpected
    0.08
    unexpected
    0.07
    Rose
    0.07
     hạng
    0.07
     feast
    0.06
    entarios
    0.06
    function
    0.06
     based
    0.06
     onstage
    0.06
    -more
    0.06
    Act Density 0.007%

    No Known Activations