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

    Neuronpedia

    INDEX
    Explanations

    single digit numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -pic
    -0.06
    ainted
    -0.06
     Santa
    -0.06
    middlewares
    -0.06
     Suns
    -0.06
     intellectual
    -0.06
    一页
    -0.06
     keyst
    -0.06
    age
    -0.06
    _places
    -0.05
    POSITIVE LOGITS
     vzděl
    0.07
    _CONTACT
    0.07
    ١
    0.07
     नगर
    0.07
    ะ
    0.07
     indiv
    0.07
    masının
    0.07
     توم
    0.07
     Dame
    0.06
    enal
    0.06
    Act Density 0.110%

    No Known Activations