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

    Neuronpedia

    INDEX
    Explanations

    Scientific methods and samples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (W
    -0.07
    .Init
    -0.07
    _sub
    -0.06
    APO
    -0.06
    _LINES
    -0.06
     Tra
    -0.06
    ------
    -0.06
    _EXP
    -0.06
     Orient
    -0.06
    _WRAP
    -0.06
    POSITIVE LOGITS
    .／
    0.07
     вироб
    0.07
    ±
    0.07
    щі
    0.06
     místo
    0.06
     Ú
    0.06
    `}
    0.06
    WINDOWS
    0.06
    protocols
    0.06
     diy
    0.06
    Act Density 0.006%

    No Known Activations