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

    Neuronpedia

    INDEX
    Explanations

    documentation, code blocks, or config

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "
    2.70
     "...
    2.08
     ("
    2.04
    "
    1.98
     '
    1.93
    ..."
    1.91
    "...
    1.83
    ...
    1.81
    -"
    1.77
    -...
    1.73
    POSITIVE LOGITS
     whats
    1.42
     how
    1.36
     nbsp
    1.29
     keto
    1.24
     How
    1.23
    .\"
    1.20
     diabetes
    1.18
     gummies
    1.18
     erectile
    1.15
     diabetic
    1.15
    Act Density 0.002%

    No Known Activations