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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    commands
    -0.06
    videos
    -0.06
     cinemat
    -0.06
    API
    -0.06
     Indianapolis
    -0.06
     Concert
    -0.06
    .ts
    -0.06
     emoji
    -0.06
    bserv
    -0.06
     ži
    -0.06
    POSITIVE LOGITS
     Solution
    0.07
     counselor
    0.06
    iciencies
    0.06
    DivElement
    0.06
    directories
    0.06
    amental
    0.06
    競
    0.06
    _w
    0.06
    _File
    0.06
    िप
    0.06
    Act Density 0.001%

    No Known Activations