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

    Neuronpedia

    INDEX
    Explanations

    multiplicity or diversity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    练习
    -0.07
    أحكام
    -0.06
     computation
    -0.06
    ⾨
    -0.06
    +b
    -0.06
     Tas
    -0.06
    的实际
    -0.06
    职业
    -0.06
     caz
    -0.06
    itters
    -0.06
    POSITIVE LOGITS
    viously
    0.08
    isks
    0.07
     erotiske
    0.07
    -alt
    0.07
    ARRY
    0.07
    traits
    0.07
     противо
    0.07
    YST
    0.07
     cvs
    0.07
    💯
    0.07
    Act Density 0.158%

    No Known Activations