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

    Neuronpedia

    INDEX
    Explanations

    Range

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    فس
    -0.07
    kop
    -0.06
    ักท
    -0.06
    ７
    -0.06
    .Bean
    -0.06
    tet
    -0.06
    	T
    -0.06
    veyor
    -0.06
    declar
    -0.06
    Ê
    -0.06
    POSITIVE LOGITS
    dül
    0.07
     Belg
    0.07
     Mayweather
    0.07
     продукт
    0.07
     ignite
    0.06
     электр
    0.06
    	write
    0.06
    getExtension
    0.06
     prix
    0.06
     coeffs
    0.06
    Act Density 0.002%

    No Known Activations