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

    Neuronpedia

    INDEX
    Explanations

    arguments against

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ěné
    1.05
    ajući
    0.96
    ající
    0.95
    álie
    0.94
    hape
    0.94
    னில்
    0.91
    うちに
    0.90
    秒
    0.89
    సాయ
    0.88
    ího
    0.87
    POSITIVE LOGITS
     Puerto
    0.89
     Part
    0.87
     Texas
    0.87
     Micro
    0.85
     Imperial
    0.85
     Green
    0.84
     Love
    0.84
     American
    0.83
     Lib
    0.82
     Navajo
    0.82
    Act Density 0.000%

    No Known Activations