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

    Neuronpedia

    INDEX
    Explanations

    addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .coordinate
    -0.07
     שהיו
    -0.07
    떰
    -0.07
    有期
    -0.07
    iership
    -0.06
    FunctionFlags
    -0.06
    '^$',
    -0.06
     zwykł
    -0.06
    各单位
    -0.06
     ::::::::
    -0.06
    POSITIVE LOGITS
    舔
    0.08
     lup
    0.07
     Try
    0.07
     preach
    0.07
    !')↵↵
    0.07
     astro
    0.07
     paw
    0.07
     chk
    0.07
     Client
    0.07
     retr
    0.06
    Act Density 0.053%

    No Known Activations