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

    Neuronpedia

    INDEX
    Explanations

    explaining why something works

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    of
    0.54
     of
    0.49
    '
    0.49
    0.43
    ach
    0.41
    rating
    0.41
    are
    0.40
    0
    0.39
    is
    0.39
    j
    0.39
    POSITIVE LOGITS
    നില്‍
    0.49
    UnifiedTopology
    0.44
    uelos
    0.42
     pleinement
    0.42
    少し
    0.40
    astă
    0.40
     Изда
    0.39
     oficialmente
    0.38
     encanta
    0.38
    Ẓ
    0.38
    Act Density 0.131%

    No Known Activations