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

    Neuronpedia

    INDEX
    Explanations

    code snippets and HTML

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ordinary
    1.20
    atively
    1.16
     broadcasts
    1.15
     conjoint
    1.14
     cohomology
    1.13
    主义
    1.11
     advances
    1.09
    était
    1.09
    est
    1.09
     가지
    1.08
    POSITIVE LOGITS
    д
    1.59
    y
    1.41
    ย
    1.28
    sen
    1.25
    نه
    1.23
     compromiso
    1.22
                        
    1.17
    iencia
    1.15
    ब
    1.14
    ยาว
    1.13
    Act Density 0.000%

    No Known Activations