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

    Neuronpedia

    INDEX
    Explanations

    error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     گ
    -0.07
     -↵↵
    -0.07
     cg
    -0.07
     icing
    -0.06
     равно
    -0.06
    ấn
    -0.06
    nad
    -0.06
    _ord
    -0.06
     ني
    -0.06
    stud
    -0.06
    POSITIVE LOGITS
    050
    0.07
    .Msg
    0.07
    aled
    0.06
    ALCHEMY
    0.06
    (Block
    0.06
     *\
    0.06
     Wright
    0.06
    emption
    0.06
    Subscribe
    0.06
     geç
    0.06
    Act Density 0.004%

    No Known Activations