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

    Neuronpedia

    INDEX
    Explanations

    lang

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mø
    -0.08
     побач
    -0.07
    Entr
    -0.06
     Drill
    -0.06
     jente
    -0.06
    ouis
    -0.06
    >>>>>>>
    -0.06
    chosen
    -0.06
     Compar
    -0.06
     preserved
    -0.06
    POSITIVE LOGITS
     lang
    0.14
     Lang
    0.14
    lang
    0.13
    Lang
    0.12
     LANG
    0.10
    .Lang
    0.10
    /lang
    0.10
    langs
    0.09
    LANG
    0.09
    (lang
    0.09
    Act Density 0.005%

    No Known Activations