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

    Neuronpedia

    INDEX
    Explanations

    Disclaimers and notices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⏭
    -0.07
     ullam
    -0.07
    组长
    -0.07
    licted
    -0.06
    ushima
    -0.06
    😿
    -0.06
    歆
    -0.06
    瘾
    -0.06
    ᚾ
    -0.06
     dialogs
    -0.06
    POSITIVE LOGITS
     technique
    0.08
     //////
    0.07
    firefox
    0.07
    在那里
    0.07
    ಹ
    0.06
    Players
    0.06
     handy
    0.06
    Æ
    0.06
    ))*(
    0.06
    ⾊
    0.06
    Act Density 0.027%

    No Known Activations