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

    Neuronpedia

    INDEX
    Explanations

    alpha

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .with
    -0.07
     ${
    -0.07
     moderation
    -0.06
    metatable
    -0.06
    omers
    -0.06
     Nazi
    -0.06
    -decoration
    -0.06
    об
    -0.06
     Lod
    -0.06
     Созд
    -0.06
    POSITIVE LOGITS
     Rahul
    0.07
    (ps
    0.06
     Θ
    0.06
     мінім
    0.06
     Elf
    0.06
     origen
    0.06
     EPS
    0.06
     mojo
    0.06
    _epsilon
    0.06
    эф
    0.06
    Act Density 0.006%

    No Known Activations