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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     없습니다
    -0.07
     následující
    -0.07
     :";↵
    -0.07
     ihtiy
    -0.06
    igy
    -0.06
    235
    -0.06
     excelente
    -0.06
     khối
    -0.06
    maktadır
    -0.06
     koy
    -0.06
    POSITIVE LOGITS
    OST
    0.06
     THC
    0.06
     GIR
    0.06
     beginners
    0.06
    (()=>
    0.06
    /$
    0.06
    [ID
    0.06
    .Struct
    0.06
     пак
    0.06
    .datasource
    0.06
    Act Density 0.004%

    No Known Activations