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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _OT
    -0.07
     tầng
    -0.07
     ethers
    -0.07
     ISC
    -0.07
     kỹ
    -0.07
    .contains
    -0.06
     downfall
    -0.06
    /mol
    -0.06
     FileMode
    -0.06
    .days
    -0.06
    POSITIVE LOGITS
    Ul
    0.07
     pist
    0.07
    決定
    0.06
    Face
    0.06
     copies
    0.06
     onwards
    0.06
    ["$
    0.06
     Trilogy
    0.06
    Gateway
    0.06
    ollow
    0.06
    Act Density 0.032%

    No Known Activations