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

    Neuronpedia

    INDEX
    Explanations

    Greek mythology characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Yunan
    0.99
    Myth
    0.94
     Atl
    0.93
     Olympian
    0.91
     mythology
    0.91
    Olymp
    0.90
     Olympi
    0.90
     Hemsworth
    0.89
    Titan
    0.85
    Greece
    0.85
    POSITIVE LOGITS
    篓
    0.71
     Frank
    0.64
    ([-
    0.64
     аро
    0.63
     Sosa
    0.62
     defects
    0.62
     Piper
    0.61
     mess
    0.59
    ვის
    0.59
     Pepper
    0.58
    Act Density 0.001%

    No Known Activations