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

    Neuronpedia

    INDEX
    Explanations

    Understanding and descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (acc
    -0.08
    Scanning
    -0.08
    ring
    -0.08
     pig
    -0.07
    猪
    -0.07
    asal
    -0.07
    /org
    -0.07
    .acc
    -0.07
    Lect
    -0.07
     така
    -0.07
    POSITIVE LOGITS
     anguish
    0.09
    urous
    0.09
     fath
    0.08
    नीय
    0.08
     époque
    0.08
     explosions
    0.08
    الية
    0.08
     imaginable
    0.08
     времена
    0.08
     hurry
    0.08
    Act Density 0.025%

    No Known Activations