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

    Neuronpedia

    INDEX
    Explanations

    size and distance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    White
    -0.07
    ortality
    -0.07
    SupportedContent
    -0.07
     migliori
    -0.07
     �
    -0.07
    贵
    -0.06
     AK
    -0.06
     rankings
    -0.06
     startups
    -0.06
    Manage
    -0.06
    POSITIVE LOGITS
    言
    0.06
     POSS
    0.06
    elik
    0.06
    _numer
    0.06
    ">'.
    0.06
     geld
    0.06
     felse
    0.06
    ブリ
    0.06
    .undo
    0.06
    erde
    0.06
    Act Density 0.040%

    No Known Activations