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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beginners
    -0.07
     Frontier
    -0.07
     foundational
    -0.07
    ƛ
    -0.07
    쩠
    -0.06
     }))
    -0.06
    urable
    -0.06
    lem
    -0.06
    百姓
    -0.06
     dific
    -0.06
    POSITIVE LOGITS
    㙍
    0.08
     oltre
    0.07
     Pepsi
    0.07
    .Entry
    0.07
     Ста
    0.07
    샬
    0.06
    @protocol
    0.06
    .slide
    0.06
    .MULT
    0.06
     Shoot
    0.06
    Act Density 0.137%

    No Known Activations