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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    密
    -0.06
    川
    -0.06
    ingu
    -0.06
     Další
    -0.06
    Aura
    -0.06
     zástup
    -0.06
    工
    -0.06
    альной
    -0.06
    ání
    -0.06
     Bean
    -0.06
    POSITIVE LOGITS
    acerb
    0.07
     WAR
    0.06
    324
    0.06
     ADVISED
    0.06
     aerial
    0.06
     اسر
    0.06
    466
    0.06
     observe
    0.06
     pedig
    0.06
     scaleY
    0.06
    Act Density 0.021%

    No Known Activations