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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uyến
    -0.06
    raç
    -0.06
     โดย
    -0.06
    Russian
    -0.06
     seguridad
    -0.06
    _type
    -0.06
     mdi
    -0.06
     اجرای
    -0.06
    沒
    -0.06
    Nice
    -0.06
    POSITIVE LOGITS
     spontaneous
    0.07
    isible
    0.07
    .setAlignment
    0.07
    τή
    0.07
     v
    0.06
     bloody
    0.06
    -third
    0.06
    -blog
    0.06
     infield
    0.06
    énom
    0.06
    Act Density 0.009%

    No Known Activations