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

    Neuronpedia

    INDEX
    Explanations

    grammatical errors/weird text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sterile
    -0.07
     Zoom
    -0.07
     Gate
    -0.07
    ावर
    -0.07
     sob
    -0.06
     insults
    -0.06
     Compression
    -0.06
    атом
    -0.06
     certain
    -0.06
    und
    -0.06
    POSITIVE LOGITS
    (p
    0.06
     fibonacci
    0.06
     �
    0.06
     (![
    0.06
     psycopg
    0.06
     mig
    0.06
    '):
↵
    0.06
     broadband
    0.06
    src
    0.06
    ']))↵↵
    0.06
    Act Density 0.001%

    No Known Activations