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

    Neuronpedia

    INDEX
    Explanations

    recreational activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    名称
    -0.07
     Livingston
    -0.07
    /logo
    -0.07
     бизнес
    -0.07
    .k
    -0.06
    -br
    -0.06
     ultra
    -0.06
     Ст
    -0.06
    ㄷ
    -0.06
    ?key
    -0.06
    POSITIVE LOGITS
     vue
    0.07
    ніше
    0.07
    '},
↵
    0.07
    rece
    0.06
     divides
    0.06
    )',↵
    0.06
     مقدم
    0.06
    \Exceptions
    0.06
     Huff
    0.06
     Justice
    0.06
    Act Density 0.046%

    No Known Activations