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

    Neuronpedia

    INDEX
    Explanations

    friendships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zus
    -0.07
    inces
    -0.06
    <r
    -0.06
    hots
    -0.06
     "",
    -0.06
    ,U
    -0.06
    .private
    -0.06
    •↵↵
    -0.06
     따라
    -0.06
     Compared
    -0.06
    POSITIVE LOGITS
    paněl
    0.07
    _atual
    0.06
    Ã
    0.06
    FFECT
    0.06
     omitted
    0.06
     tic
    0.06
     promptly
    0.06
     paramMap
    0.06
     RESET
    0.06
    werk
    0.06
    Act Density 0.013%

    No Known Activations