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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝕭
    -0.08
     fuera
    -0.08
    دين
    -0.07
    ﺵ
    -0.07
    ㎠
    -0.07
     swearing
    -0.07
     ואף
    -0.07
     cheered
    -0.07
     Filme
    -0.07
     casa
    -0.07
    POSITIVE LOGITS
    巧合
    0.07
    irate
    0.07
    Short
    0.07
    noticed
    0.07
    疫情影响
    0.07
    /↵↵↵
    0.07
     '↵↵
    0.07
    long
    0.07
    Session
    0.07
    ightly
    0.07
    Act Density 0.015%

    No Known Activations