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

    Neuronpedia

    INDEX
    Explanations

    answering questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    938
    -0.06
     FIL
    -0.06
    trinsic
    -0.06
    ınca
    -0.06
    lerinde
    -0.06
    čil
    -0.06
       
↵
    -0.06
    러스
    -0.06
    atrib
    -0.06
    .prop
    -0.06
    POSITIVE LOGITS
    [opt
    0.07
     emailed
    0.07
     esta
    0.07
    !")
    0.07
     شیمی
    0.07
    omentum
    0.06
    ёт
    0.06
    !!!!
    0.06
     Excellent
    0.06
    GetName
    0.06
    Act Density 0.053%

    No Known Activations