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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roh
    -0.07
     Deluxe
    -0.07
     Allison
    -0.07
     yans
    -0.07
    だろう
    -0.07
    USD
    -0.06
     mooie
    -0.06
    .Day
    -0.06
     BAS
    -0.06
    InterruptedException
    -0.06
    POSITIVE LOGITS
    lying
    0.06
     explicitly
    0.06
     пре
    0.06
    meteor
    0.06
    олж
    0.06
    /react
    0.06
    ựa
    0.06
    REAK
    0.06
     تعداد
    0.06
    σιμοποι
    0.06
    Act Density 0.027%

    No Known Activations