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

    Neuronpedia

    INDEX
    Explanations

    code and declaration keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oligodend
    0.43
     fortement
    0.39
     cambi
    0.38
     কর্তৃত্ব
    0.38
    Aldrich
    0.37
    ლები
    0.37
     Promenade
    0.37
     creazione
    0.37
     የሚያ
    0.37
    arreglo
    0.36
    POSITIVE LOGITS
    ?
    0.35
    类
    0.34
    ?$
    0.33
    GNU
    0.32
    fäh
    0.32
     filas
    0.32
    iml
    0.31
    声明
    0.31
    FILENAME
    0.30
     fileurl
    0.30
    Act Density 0.000%

    No Known Activations