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

    Neuronpedia

    INDEX
    Explanations

    until

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pdf
    -0.07
    define
    -0.07
     IGNORE
    -0.07
     bash
    -0.06
    Deep
    -0.06
    )return
    -0.06
    -inverse
    -0.06
     -‐
    -0.06
    Bur
    -0.06
    -alpha
    -0.06
    POSITIVE LOGITS
    710
    0.07
     gặp
    0.06
    ussy
    0.06
     apologized
    0.06
    ising
    0.06
    ********************************
    0.06
    _RANDOM
    0.06
    于是
    0.06
     glowing
    0.06
    erreur
    0.06
    Act Density 0.013%

    No Known Activations