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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     _{
    -0.06
    scrollView
    -0.06
     Geoffrey
    -0.06
    }_{
    -0.06
    Tell
    -0.06
    Wednesday
    -0.06
    _{
    -0.06
     Rory
    -0.05
    Keith
    -0.05
     подум
    -0.05
    POSITIVE LOGITS
     geral
    0.08
     شمالی
    0.07
     igual
    0.07
     TABLE
    0.07
     thankful
    0.07
     آمار
    0.07
    램
    0.07
    цы
    0.07
     СРСР
    0.07
    _total
    0.07
    Act Density 0.203%

    No Known Activations