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

    Neuronpedia

    INDEX
    Explanations

    .asList

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .GUI
    -0.07
     width
    -0.07
    動き
    -0.07
     carp
    -0.07
    Ắ
    -0.07
    (Tree
    -0.07
     leader
    -0.07
    еля
    -0.07
    .buf
    -0.07
     cumpl
    -0.07
    POSITIVE LOGITS
    рма
    0.08
     *,↵
    0.07
    袱
    0.07
    ocalypse
    0.06
    .jetbrains
    0.06
     zaman
    0.06
    /Table
    0.06
    也只是
    0.06
    0.06
     bastante
    0.06
    Act Density 0.002%

    No Known Activations