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

    Neuronpedia

    INDEX
    Explanations

    tips and advice articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leared
    -0.07
    mouseenter
    -0.06
    っと
    -0.06
     {}).
    -0.06
    _SPECIAL
    -0.06
    BIG
    -0.06
    bang
    -0.06
    INVALID
    -0.06
    King
    -0.06
     crates
    -0.06
    POSITIVE LOGITS
    alığı
    0.07
    面的
    0.07
     speakers
    0.06
    -BEGIN
    0.06
    aters
    0.06
    lov
    0.06
    ewitness
    0.06
     tempo
    0.06
    <Game
    0.06
     summar
    0.06
    Act Density 0.004%

    No Known Activations