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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Рос
    -0.07
    そんな
    -0.07
     encryption
    -0.06
    						
↵
    -0.06
     })
↵
↵
    -0.06
    .pair
    -0.06
    bestos
    -0.06
    '));↵↵
    -0.06
    ')}>↵
    -0.06
     Chips
    -0.06
    POSITIVE LOGITS
    pl
    0.07
     redistribute
    0.07
    _mime
    0.06
    漫画
    0.06
     आश
    0.06
     funkci
    0.06
     Hayden
    0.06
    ━━
    0.06
     necesita
    0.06
    _HINT
    0.06
    Act Density 0.066%

    No Known Activations