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

    Neuronpedia

    INDEX
    Explanations

    too

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Möglichkeit
    -0.07
    -ph
    -0.07
    _REQUIRE
    -0.07
     narrator
    -0.07
     کارگرد
    -0.06
     Sanat
    -0.06
     testimony
    -0.06
    .valid
    -0.06
    entication
    -0.06
     gras
    -0.06
    POSITIVE LOGITS
    IA
    0.07
    *g
    0.06
    сию
    0.06
    /models
    0.06
     시작
    0.06
     Restoration
    0.06
    (Integer
    0.06
    inn
    0.06
     dri
    0.05
     răng
    0.05
    Act Density 0.007%

    No Known Activations