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

    Neuronpedia

    INDEX
    Explanations

    Press release fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    袖
    -0.06
     dul
    -0.06
    際
    -0.06
     swe
    -0.06
     ап
    -0.06
     interfer
    -0.06
    独立
    -0.06
    ----------↵
    -0.05
    ................
    -0.05
     sou
    -0.05
    POSITIVE LOGITS
     gigg
    0.07
    .downcase
    0.07
    plug
    0.07
     gratuites
    0.06
     SingleChildScrollView
    0.06
    roy
    0.06
    CONFIG
    0.06
     Jacques
    0.06
    atorio
    0.06
    tera
    0.06
    Act Density 0.260%

    No Known Activations