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

    Neuronpedia

    INDEX
    Explanations

    Second coming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     מיליון
    -0.07
     ciudad
    -0.07
    增添
    -0.07
     datetime
    -0.07
     משחק
    -0.07
    _TURN
    -0.06
    study
    -0.06
    .stdout
    -0.06
    /reset
    -0.06
     январ
    -0.06
    POSITIVE LOGITS
    (styles
    0.07
     저
    0.06
    UAGE
    0.06
     الطبيعي
    0.06
    /packages
    0.06
    _both
    0.06
    ˑ
    0.06
    村村民
    0.06
    委宣传
    0.06
     COR
    0.06
    Act Density 0.008%

    No Known Activations