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

    Neuronpedia

    INDEX
    Explanations

    salinity levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anmar
    -0.07
    .Page
    -0.07
    มา
    -0.07
     shorten
    -0.07
     Giul
    -0.06
    _copy
    -0.06
    数组
    -0.06
    (version
    -0.06
     verbosity
    -0.06
    แสดง
    -0.06
    POSITIVE LOGITS
    Theory
    0.07
    "\
    0.06
    toolbox
    0.06
     alkal
    0.06
    .Com
    0.06
     faculties
    0.06
     işaret
    0.06
     honesty
    0.06
     ps
    0.06
    filme
    0.06
    Act Density 0.085%

    No Known Activations