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

    Neuronpedia

    INDEX
    Explanations

    legal citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itu
    -0.07
    Hat
    -0.06
    (INT
    -0.06
    umuz
    -0.06
    ')}}↵
    -0.06
     posX
    -0.06
    ату
    -0.06
    allocate
    -0.06
     bos
    -0.06
    !:
    -0.06
    POSITIVE LOGITS
     some
    0.07
     followers
    0.06
    ере
    0.06
     dialogue
    0.06
    Timing
    0.06
    -found
    0.06
    .LoggerFactory
    0.06
     reunited
    0.06
     والس
    0.06
     unauthorized
    0.06
    Act Density 0.001%

    No Known Activations