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

    Neuronpedia

    INDEX
    Explanations

    "hot" or popular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .const
    -0.07
    _missing
    -0.07
    (Arg
    -0.07
    園
    -0.06
    (SE
    -0.06
    橋
    -0.06
    .foo
    -0.06
     mos
    -0.06
    \Image
    -0.06
     µ
    -0.06
    POSITIVE LOGITS
     pregn
    0.08
     Helping
    0.07
     Ży
    0.07
    抚摸
    0.07
    但是
    0.07
    潋
    0.07
    💜
    0.07
    战火
    0.06
    מבט
    0.06
    搠
    0.06
    Act Density 0.022%

    No Known Activations