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

    Neuronpedia

    INDEX
    Explanations

    Opposing viewpoints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fer
    -0.07
    /student
    -0.07
    Sem
    -0.07
    oter
    -0.07
    uler
    -0.07
    悌
    -0.06
     whe
    -0.06
     Svg
    -0.06
    /spec
    -0.06
    _ud
    -0.06
    POSITIVE LOGITS
    华丽
    0.07
    iant
    0.07
    进行全面
    0.07
    _modes
    0.07
    ________________________________________________________________
    0.07
     formatted
    0.06
     '</
    0.06
    パワー
    0.06
    昌
    0.06
    事发
    0.06
    Act Density 0.083%

    No Known Activations