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

    Neuronpedia

    INDEX
    Explanations

    datasets, hash, plaque

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Left
    0.45
    None
    0.44
    Journal
    0.44
    1
    0.43
    LET
    0.43
    ↵
    0.42
    wright
    0.42
    Cause
    0.42
    Before
    0.41
    Two
    0.40
    POSITIVE LOGITS
    ุน
    0.58
     devem
    0.49
    ین
    0.49
    نی
    0.49
    િતિ
    0.47
     são
    0.46
    ریع
    0.46
     mię
    0.46
     możliwości
    0.46
     quella
    0.45
    Act Density 0.007%

    No Known Activations