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

    Neuronpedia

    INDEX
    Explanations

    correlation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Carthy
    -0.30
    éĢļåijĬ
    -0.26
    款
    -0.25
    Äĩi
    -0.25
    avian
    -0.24
    æŃ£ç¡®çļĦ
    -0.24
     getWindow
    -0.24
    Ĭ¶
    -0.24
     lastIndex
    -0.23
     kötü
    -0.23
    POSITIVE LOGITS
    æº
    0.27
    arges
    0.27
    è´£
    0.26
    _=
    0.26
    eof
    0.24
     spaghetti
    0.24
     hour
    0.24
    æĻļ
    0.24
     y
    0.24
    _bd
    0.24
    Act Density 0.061%

    No Known Activations