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

    Neuronpedia

    INDEX
    Explanations

    quoted phrases or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    “
    1.98
     “
    1.76
    ，“
    1.71
    (“
    1.59
     (“
    1.50
     „
    1.49
    。“
    1.48
    、“
    1.45
    “(
    1.37
     “(
    1.36
    POSITIVE LOGITS
    ...'
    1.55
    ...',
    1.52
    ।'
    1.38
    ':
    1.37
    '.
    1.36
    ,'"
    1.34
    \_
    1.34
    ..."
    1.29
    '-
    1.26
    .'"
    1.24
    Act Density 0.629%

    No Known Activations