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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Dependency
    0.60
    Engineering
    0.60
    ７
    0.59
    Scholar
    0.58
    IDEA
    0.56
    Homework
    0.55
    Desert
    0.55
    RI
    0.55
    Burning
    0.55
    Fantastic
    0.55
    POSITIVE LOGITS
    .’
    0.96
    ’-
    0.92
    …
    0.92
    ’.
    0.90
    .\
    0.83
    .”
    0.83
    \
    0.83
    .-
    0.82
    ’
    0.81
    ..
    0.81
    Act Density 0.000%

    No Known Activations