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

    Neuronpedia

    INDEX
    Explanations

    variable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fac
    -0.07
     getContent
    -0.07
    Cli
    -0.07
     superb
    -0.06
     Аб
    -0.06
    esc
    -0.06
    -0.06
     fn
    -0.06
     fac
    -0.06
    resolved
    -0.06
    POSITIVE LOGITS
     männer
    0.07
    Mrs
    0.06
     Tick
    0.06
    <Key
    0.06
    oggles
    0.06
     Ragnar
    0.06
     PROGMEM
    0.06
    &&&&
    0.06
     страниц
    0.06
    ANNER
    0.06
    Act Density 0.013%

    No Known Activations