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

    Neuronpedia

    INDEX
    Explanations

    Narratives and personal experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     was
    -1.39
     wasn
    -1.17
     had
    -1.13
     were
    -1.13
     seemed
    -1.08
    was
    -1.06
     weren
    -1.03
     consisted
    -1.02
    Was
    -0.99
     differed
    -0.99
    POSITIVE LOGITS
     zostanie
    0.69
     will
    0.67
     are
    0.66
    DockStyle
    0.64
    ίναι
    0.63
    žuje
    0.63
     ostavi
    0.62
    phorus
    0.61
    RectangleBorder
    0.60
    ází
    0.59
    Act Density 0.035%

    No Known Activations