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

    Neuronpedia

    INDEX
    Explanations

    say "notation"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    上了
    -0.08
    Baseline
    -0.07
     Sands
    -0.07
    Attempt
    -0.06
     traces
    -0.06
    NSArray
    -0.06
    Desde
    -0.06
    екту
    -0.06
    ичного
    -0.06
     messageType
    -0.06
    POSITIVE LOGITS
    _traj
    0.06
     admin
    0.06
    ubbles
    0.06
    ७
    0.06
    .mac
    0.06
     clips
    0.06
    ,f
    0.06
     Poe
    0.06
    .char
    0.06
    <m
    0.05
    Act Density 0.094%

    No Known Activations