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

    Neuronpedia

    INDEX
    Explanations

    bounds checking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    diği
    -0.06
     subscri
    -0.06
     ACK
    -0.06
    갠
    -0.06
     Representatives
    -0.06
    잨
    -0.06
     Franc
    -0.06
     blanc
    -0.06
     smo
    -0.06
     ideally
    -0.06
    POSITIVE LOGITS
    .ENTER
    0.08
    صيان
    0.08
    life
    0.08
    Shar
    0.08
    >equals
    0.08
    Swipe
    0.07
    يز
    0.07
    ened
    0.07
     Milwaukee
    0.07
    ẩu
    0.07
    Act Density 0.019%

    No Known Activations