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

    Neuronpedia

    INDEX
    Explanations

    let

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     قد
    -0.07
     Protect
    -0.07
    Associ
    -0.07
     pans
    -0.06
    _friend
    -0.06
    FINE
    -0.06
     ister
    -0.06
     CONVERT
    -0.06
     getir
    -0.06
    .Receive
    -0.06
    POSITIVE LOGITS
     일반
    0.07
    (br
    0.07
     gaining
    0.06
    (is
    0.06
    ーター
    0.06
    dot
    0.06
    rut
    0.06
    _div
    0.06
    maları
    0.06
    (min
    0.06
    Act Density 0.011%

    No Known Activations