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

    Neuronpedia

    INDEX
    Explanations

    docstring endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     eldest
    0.53
    ವಿದೆ
    0.52
     variable
    0.51
    某
    0.50
    ます
    0.50
     deviates
    0.50
    ahuje
    0.50
    ি
    0.49
     value
    0.49
     variously
    0.49
    POSITIVE LOGITS
     The
    0.84
     ktore
    0.75
     Which
    0.74
     WHICH
    0.70
    The
    0.70
     तकनी
    0.70
     RATES
    0.68
     které
    0.65
     the
    0.64
    Which
    0.63
    Act Density 0.040%

    No Known Activations