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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hashes
    -0.07
    ,get
    -0.07
    を使
    -0.06
    ける
    -0.06
     backwards
    -0.06
    .move
    -0.06
    switch
    -0.06
    線
    -0.06
    ½
    -0.06
     addObject
    -0.06
    POSITIVE LOGITS
     Regions
    0.07
    _WARNINGS
    0.07
     Quận
    0.07
     recounted
    0.06
    那种
    0.06
    SEP
    0.06
     публі
    0.06
     Sor
    0.06
     ¥
    0.06
     �
    0.06
    Act Density 0.001%

    No Known Activations