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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    иб
    -0.07
    Raw
    -0.06
    oints
    -0.06
    ########################################
    -0.06
    <!--↵
    -0.06
    体系
    -0.06
     कथ
    -0.06
     insult
    -0.06
     수정
    -0.06
    vědom
    -0.06
    POSITIVE LOGITS
     많은
    0.07
     Tir
    0.06
    κυ
    0.06
     explodes
    0.06
    .Art
    0.06
    nation
    0.06
    /pr
    0.06
     Dive
    0.06
    /perl
    0.06
     "";
↵
↵
    0.06
    Act Density 0.022%

    No Known Activations