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

    Neuronpedia

    INDEX
    Explanations

    how and common methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    করি
    0.45
    ğaz
    0.43
    stantially
    0.41
    یشن
    0.41
     ฮะ
    0.40
    ziła
    0.40
     কৈ
    0.39
    thapi
    0.39
    ளிட
    0.39
     Hendricks
    0.38
    POSITIVE LOGITS
    _,
    0.40
    alumno
    0.38
     pretende
    0.38
    0.38
     student
    0.38
    student
    0.38
     teacher
    0.38
    ologique
    0.37
    {
    0.37
     provided
    0.37
    Act Density 0.002%

    No Known Activations