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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alumnos
    -0.07
    enzhen
    -0.06
     подав
    -0.06
    Japanese
    -0.06
     fatigue
    -0.06
     Erl
    -0.06
     패
    -0.06
    dělení
    -0.06
     musel
    -0.06
     phương
    -0.06
    POSITIVE LOGITS
     essays
    0.07
    _xx
    0.07
    .xx
    0.07
    =[]↵
    0.07
     Вики
    0.06
     +++
    0.06
    write
    0.06
     Fever
    0.06
    notify
    0.06
    enn
    0.06
    Act Density 0.000%

    No Known Activations