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

    Neuronpedia

    INDEX
    Explanations

    https

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    まだ
    -0.06
    또
    -0.06
     tanto
    -0.06
     ö
    -0.06
     felony
    -0.06
    áč
    -0.06
     �
    -0.06
    bro
    -0.06
    TERNAL
    -0.06
     dull
    -0.06
    POSITIVE LOGITS
     механіз
    0.08
     ajust
    0.07
    (Schedulers
    0.07
    .CONTENT
    0.07
    ?↵↵↵
    0.06
    ريكية
    0.06
     ug
    0.06
    »
    0.06
     reasonably
    0.06
     Animator
    0.06
    Act Density 0.010%

    No Known Activations