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

    Neuronpedia

    INDEX
    Explanations

    removal, separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    datatype
    -0.07
     Likely
    -0.07
    Encrypt
    -0.07
     문자
    -0.07
     REAL
    -0.06
     sustaining
    -0.06
    iversal
    -0.06
    LiveData
    -0.06
     demonstrate
    -0.06
     analyzing
    -0.06
    POSITIVE LOGITS
    ilion
    0.06
    véd
    0.06
     startPosition
    0.06
    rai
    0.06
    ')
    0.06
    indle
    0.06
    출장샵
    0.06
    cols
    0.06
    ves
    0.06
     phúc
    0.06
    Act Density 0.179%

    No Known Activations