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

    Neuronpedia

    INDEX
    Explanations

    Korean/Japanese particles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
     ​​
    -0.07
     αυ
    -0.07
    wstring
    -0.07
    пис
    -0.07
     여부
    -0.07
    ਨਾਂ
    -0.07
    Hil
    -0.07
     Burner
    -0.07
     zuverläss
    -0.07
    POSITIVE LOGITS
    끔
    0.11
     되어
    0.09
    �
    0.09
    force
    0.08
     force
    0.08
    Upd
    0.08
     Force
    0.08
     ADV
    0.08
    .PERMISSION
    0.08
    にな
    0.08
    Act Density 0.003%
    No Known Activations