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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Petit
    -0.07
     stalls
    -0.06
    uncate
    -0.06
     gospel
    -0.06
     Enabled
    -0.06
     Rainbow
    -0.06
    权
    -0.06
    몰
    -0.06
    ball
    -0.06
    stantiate
    -0.06
    POSITIVE LOGITS
    (enum
    0.07
    frica
    0.07
    (BASE
    0.06
    .setX
    0.06
     manip
    0.06
     世界
    0.06
    .phi
    0.06
    .anchor
    0.06
     Ansi
    0.06
    [{
    0.06
    Act Density 0.000%

    No Known Activations