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

    Neuronpedia

    INDEX
    Explanations

    First-person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mont
    -0.27
    ypi
    -0.27
    ä¸įä»ħè¦ģ
    -0.27
     survival
    -0.27
    haft
    -0.26
    asu
    -0.26
    è¾Ī
    -0.25
     xuyên
    -0.25
    ewise
    -0.24
    åĪĽä¼¤
    -0.24
    POSITIVE LOGITS
    Tur
    0.27
    à´±
    0.24
    parallel
    0.24
    åŁķ
    0.24
    ä¸įå®ļ
    0.24
    æķ¦
    0.24
    _pv
    0.24
    tur
    0.23
     StringTokenizer
    0.23
    .middle
    0.23
    Act Density 0.118%

    No Known Activations