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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     אף
    -0.07
    ,tmp
    -0.07
    ϻ
    -0.07
    ॐ
    -0.06
    🎃
    -0.06
    힝
    -0.06
     لمدة
    -0.06
    夕阳
    -0.06
    NING
    -0.06
    OKIE
    -0.06
    POSITIVE LOGITS
     anticipated
    0.08
    文学
    0.07
    ometrics
    0.07
    贪
    0.07
    Note
    0.07
     FE
    0.07
     Beg
    0.07
     Friend
    0.06
    Storyboard
    0.06
    ]:↵↵
    0.06
    Act Density 0.002%

    No Known Activations