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

    Neuronpedia

    INDEX
    Explanations

    newly discovered knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     principals
    0.42
     grueling
    0.40
    ریل
    0.40
     mesta
    0.39
     misfortune
    0.39
     عارف
    0.38
    Entries
    0.38
     displeasure
    0.38
     ils
    0.38
    没什么
    0.38
    POSITIVE LOGITS
     overlooked
    0.49
     идея
    0.46
     unexpected
    0.45
    pointed
    0.45
     clever
    0.44
     surprisingly
    0.44
     unexpectedly
    0.43
     considered
    0.43
     विचार
    0.42
    idea
    0.42
    Act Density 0.018%

    No Known Activations