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

    Neuronpedia

    INDEX
    Explanations

    math and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    osite
    -0.32
    Ĥ¤
    -0.29
    ppers
    -0.28
    åĶij
    -0.27
    DateFormat
    -0.25
    æķıæĦŁ
    -0.25
    ä¼ĺæĥłæĶ¿çŃĸ
    -0.25
    pliers
    -0.25
     Bentley
    -0.24
    NDER
    -0.24
    POSITIVE LOGITS
     forg
    0.30
    ÑĢÑĥб
    0.29
     Entr
    0.28
    inged
    0.27
    æ»ļçIJĥ
    0.26
    (dirname
    0.25
    astro
    0.25
    å¶Ĥ
    0.25
     thấp
    0.24
    hardware
    0.24
    Act Density 0.018%

    No Known Activations