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

    Neuronpedia

    INDEX
    Explanations

    Code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ραβ
    -0.07
    �
    -0.06
     κυ
    -0.06
    رح
    -0.06
    aday
    -0.06
    _TX
    -0.06
     AAA
    -0.06
    shoot
    -0.06
    鋼
    -0.06
     دوم
    -0.06
    POSITIVE LOGITS
    offset
    0.08
     strán
    0.07
     Clerk
    0.07
    arDown
    0.06
    .Strings
    0.06
     bij
    0.06
     predomin
    0.06
     mất
    0.06
    ตำแหน
    0.06
     Fakült
    0.06
    Act Density 0.180%

    No Known Activations