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

    Neuronpedia

    INDEX
    Explanations

    engine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	assertTrue
    -0.07
    енсив
    -0.07
    Abr
    -0.07
     Abr
    -0.06
    agini
    -0.06
     prod
    -0.06
    redict
    -0.06
     spam
    -0.06
     Kabul
    -0.06
     frequencies
    -0.06
    POSITIVE LOGITS
    =http
    0.07
    มาย
    0.06
    SharedPreferences
    0.06
     published
    0.06
    .HttpServletRequest
    0.06
    .spring
    0.06
    etAddress
    0.06
    Fields
    0.06
     червня
    0.06
    あげ
    0.06
    Act Density 0.008%

    No Known Activations