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

    Neuronpedia

    INDEX
    Explanations

    prevent discrimination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     blackberries
    0.41
     łat
    0.41
     `'\\
    0.40
     factory
    0.39
     Eggs
    0.39
     bittern
    0.39
    厂
    0.39
     जनक
    0.38
    涡
    0.38
    工場
    0.38
    POSITIVE LOGITS
    FirebaseAuth
    0.46
    lich
    0.39
    लिया
    0.38
    atah
    0.38
    atih
    0.38
    xs
    0.37
    ktx
    0.37
    ား
    0.37
    atip
    0.36
    lp
    0.36
    Act Density 0.000%

    No Known Activations