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

    Neuronpedia

    INDEX
    Explanations

    Citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    紹
    -0.07
    つけ
    -0.07
    绍
    -0.07
     sleeve
    -0.07
    mate
    -0.07
    woff
    -0.06
    _amount
    -0.06
    ποίηση
    -0.06
    —it
    -0.06
    ))*(
    -0.06
    POSITIVE LOGITS
    ُّ
    0.06
     �
    0.06
    َّ
    0.06
    cı
    0.05
    َّ
    0.05
     هر
    0.05
     efficient
    0.05
                   
↵
    0.05
     dair
    0.05
    igaret
    0.05
    Act Density 0.029%

    No Known Activations