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

    Neuronpedia

    INDEX
    Explanations

    Scientific research writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dicho
    -0.07
    ()))↵↵
    -0.07
    اذا
    -0.06
     chose
    -0.06
    .Large
    -0.06
    urch
    -0.06
    νονται
    -0.06
     Overs
    -0.06
     Elementary
    -0.06
     appropriations
    -0.06
    POSITIVE LOGITS
     tape
    0.07
    =Math
    0.07
    ْل
    0.06
     becer
    0.06
     Ссылки
    0.06
     breaches
    0.06
     sexes
    0.06
     Permission
    0.06
     tricks
    0.06
     ★
    0.06
    Act Density 0.058%

    No Known Activations