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

    Neuronpedia

    INDEX
    Explanations

    well

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    好象
    -0.31
    Remarks
    -0.30
     seats
    -0.30
    座
    -0.27
     remarks
    -0.27
     seat
    -0.27
     Remarks
    -0.27
    æ²Ķ
    -0.26
    å©Ĩ
    -0.25
    çĺ¤
    -0.25
    POSITIVE LOGITS
    keleton
    0.30
    //}↵↵
    0.30
    ece
    0.27
    otherwise
    0.26
    esian
    0.26
    |[
    0.26
    èĢĮåİ»
    0.26
    //}↵
    0.25
    eler
    0.25
    ä¸İåħ¶
    0.24
    Act Density 1.133%

    No Known Activations