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

    Neuronpedia

    INDEX
    Explanations

    microservices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Toronto
    0.54
     Liverpool
    0.54
    7
    0.52
     Livermore
    0.51
    8
    0.51
     Hepat
    0.50
     Budapest
    0.49
     in
    0.49
     Northeast
    0.48
     South
    0.48
    POSITIVE LOGITS
    ußer
    0.51
    儼
    0.51
    bole
    0.49
    avin
    0.48
    legg
    0.47
     მხ
    0.47
    ர்வ
    0.47
    Ꮡ
    0.46
    GLIGENCE
    0.45
     przyjem
    0.44
    Act Density 0.003%

    No Known Activations