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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    integer
    -0.07
     лише
    -0.07
     schem
    -0.07
     caves
    -0.06
    avour
    -0.06
     '"+
    -0.06
    fore
    -0.06
    …
    -0.06
    ('"
    -0.06
     القدم
    -0.06
    POSITIVE LOGITS
    :↵
    0.07
     kata
    0.07
    reesome
    0.06
    Porno
    0.06
     çerç
    0.06
     후보
    0.06
    '));↵
    0.06
     nád
    0.06
    :↵↵
    0.06
    	control
    0.06
    Act Density 0.000%

    No Known Activations