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

    Neuronpedia

    INDEX
    Explanations

    embed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CLEAN
    -0.08
    iye
    -0.07
     Sick
    -0.06
     respiratory
    -0.06
    ultipart
    -0.06
     Sheets
    -0.06
     +=
    -0.06
     Rac
    -0.06
     Mặt
    -0.06
    _horizontal
    -0.06
    POSITIVE LOGITS
    מ
    0.08
    /embed
    0.07
     em
    0.07
     embedded
    0.07
    embedded
    0.07
    Em
    0.07
     Em
    0.07
    ,eg
    0.07
     ек
    0.07
     imb
    0.07
    Act Density 0.006%

    No Known Activations