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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Snowden
    -0.07
     Bilim
    -0.07
     Patton
    -0.07
     sluggish
    -0.06
     cleanly
    -0.06
    (headers
    -0.06
     straightforward
    -0.06
    .showMessageDialog
    -0.06
     also
    -0.06
     шк
    -0.06
    POSITIVE LOGITS
    建筑
    0.07
     imagen
    0.07
    }\"
    0.07
     요구
    0.07
     상대
    0.06
    狀
    0.06
    ()};↵
    0.06
     دانش
    0.06
    」，
    0.06
     hallway
    0.06
    Act Density 0.001%

    No Known Activations