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

    Neuronpedia

    INDEX
    Explanations

    must/should (Korean)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     суще
    -0.07
     tranh
    -0.07
    歷
    -0.06
    holes
    -0.06
    _INITIALIZER
    -0.06
     svaz
    -0.06
     Spare
    -0.06
     circulating
    -0.06
     حو
    -0.06
     прек
    -0.06
    POSITIVE LOGITS
    Finding
    0.07
    Only
    0.06
       ↵    ↵
    0.06
     lĩnh
    0.06
    .submit
    0.06
     defends
    0.06
    (po
    0.06
     Security
    0.06
     사람은
    0.06
    ais
    0.06
    Act Density 0.010%

    No Known Activations