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

    Neuronpedia

    INDEX
    Explanations

    wiki markup characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    čnom
    0.40
    stands
    0.40
     znamená
    0.39
    standing
    0.38
     halaman
    0.38
     seasonality
    0.38
    meniz
    0.38
    iculos
    0.38
    ര്‍ച്ച
    0.37
    getParameters
    0.37
    POSITIVE LOGITS
     {|
    0.42
     pectoral
    0.41
    {|
    0.40
     tint
    0.40
    ണ്ണ
    0.40
     valign
    0.39
     discipline
    0.38
     Discipl
    0.37
    iffen
    0.35
     splinter
    0.35
    Act Density 0.000%

    No Known Activations