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

    Neuronpedia

    INDEX
    Explanations

    thief

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .isNotBlank
    -0.08
    [char
    -0.06
    $image
    -0.06
     FORCE
    -0.06
    ázal
    -0.06
     โ
    -0.06
     Celt
    -0.06
    ické
    -0.06
    obble
    -0.06
    、この
    -0.06
    POSITIVE LOGITS
    940
    0.08
     thief
    0.07
    	Use
    0.07
    980
    0.07
    .expect
    0.07
    лов
    0.06
    wives
    0.06
     Assassin
    0.06
    LOC
    0.06
    Thrown
    0.06
    Act Density 0.005%

    No Known Activations