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

    Neuronpedia

    INDEX
    Explanations

    comma followed by code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BHP
    0.90
     photo
    0.89
     Y
    0.88
     share
    0.87
    OG
    0.86
     pine
    0.83
     shares
    0.83
     silicone
    0.83
     lion
    0.83
     lions
    0.83
    POSITIVE LOGITS
     Descriptive
    1.54
    newtheorem
    1.47
     fréquentes
    1.47
     leichte
    1.41
     samostat
    1.37
     scrittura
    1.37
     numerose
    1.37
     annotate
    1.36
     ampia
    1.35
     kategor
    1.35
    Act Density 0.083%

    No Known Activations