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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _stuff
    -0.07
    .EOF
    -0.06
    Nuevo
    -0.06
     takım
    -0.06
    -reg
    -0.06
     ment
    -0.06
     매우
    -0.06
    eful
    -0.06
    -Token
    -0.06
     evet
    -0.06
    POSITIVE LOGITS
     eldre
    0.07
    utzer
    0.07
    彻
    0.07
     rallies
    0.07
     Marlins
    0.06
    ریب
    0.06
     інтер
    0.06
    ágenes
    0.06
     интер
    0.06
     reopening
    0.06
    Act Density 0.048%

    No Known Activations