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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etzt
    -0.08
     builtin
    -0.07
     magn
    -0.07
     engineer
    -0.07
    EN
    -0.07
    _matching
    -0.07
    をしている
    -0.06
     CHAR
    -0.06
     Turning
    -0.06
     Remaining
    -0.06
    POSITIVE LOGITS
    喉
    0.07
    addir
    0.07
     bais
    0.07
    -any
    0.07
    预言
    0.07
    嘶
    0.07
    开水
    0.07
    .Xr
    0.07
    .Excel
    0.07
    庭审
    0.07
    Act Density 0.095%

    No Known Activations