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

    Neuronpedia

    INDEX
    Explanations

    say "c" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Js
    -0.06
     public
    -0.06
     事
    -0.06
     下
    -0.06
    TURN
    -0.06
     Registry
    -0.06
    `↵↵
    -0.06
    ῶν
    -0.06
     practical
    -0.06
     skyrocket
    -0.06
    POSITIVE LOGITS
    PerPixel
    0.07
    bpp
    0.06
     Assass
    0.06
     Loaded
    0.06
    _Man
    0.06
    .ObjectId
    0.06
    feit
    0.06
    \Entities
    0.06
    Interface
    0.06
    ां
    0.06
    Act Density 0.012%

    No Known Activations