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

    Neuronpedia

    INDEX
    Explanations

    chemical reactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    wr
    -0.08
    wealth
    -0.07
     Friendship
    -0.07
    맞
    -0.07
    �
    -0.07
    Library
    -0.07
     Resort
    -0.06
    რ
    -0.06
    明日
    -0.06
    なくなる
    -0.06
    POSITIVE LOGITS
     spit
    0.07
     blev
    0.07
     anus
    0.07
    -semibold
    0.07
    Edited
    0.07
     Alfred
    0.07
     â
    0.07
    Multiply
    0.07
     absolute
    0.06
    _THAN
    0.06
    Act Density 0.073%

    No Known Activations