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

    Neuronpedia

    INDEX
    Explanations

    commas and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WATCH
    -0.07
    jal
    -0.06
     галуз
    -0.06
     blacklist
    -0.06
     tubing
    -0.06
     oe
    -0.06
     vraiment
    -0.06
    .Offset
    -0.06
     forgetting
    -0.05
    periences
    -0.05
    POSITIVE LOGITS
    DW
    0.08
     explains
    0.07
     shadows
    0.07
    객
    0.07
    due
    0.06
     дальней
    0.06
    {
↵
    0.06
    [strlen
    0.06
     Extend
    0.06
     release
    0.06
    Act Density 0.016%

    No Known Activations