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

    Neuronpedia

    INDEX
    Explanations

    voice, data, questioned, formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     .........
    0.80
     "*************
    0.78
    !</
    0.77
    .</
    0.76
    ."""
    0.76
    ++/
    0.75
    ⵡ
    0.75
     :}
    0.74
     😍
    0.74
     ..........
    0.74
    POSITIVE LOGITS
    They
    1.66
     They
    1.54
    It
    1.43
    There
    1.33
     It
    1.30
    The
    1.24
    He
    1.23
    Of
    1.22
    That
    1.20
     There
    1.20
    Act Density 0.029%

    No Known Activations