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

    Neuronpedia

    INDEX
    Explanations

    adding, removing, or holding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     variability
    0.49
     inconsistent
    0.48
     agent
    0.47
    ้
    0.47
     iterable
    0.47
     monotonicity
    0.46
    Todo
    0.46
     recycling
    0.46
     robotics
    0.45
     booting
    0.45
    POSITIVE LOGITS
    INR
    0.49
    ﺳ
    0.47
    '
    0.46
    équation
    0.44
    をご
    0.44
    を持って
    0.43
    MappingURL
    0.43
    <sub>
    0.43
    とともに
    0.43
    が大
    0.43
    Act Density 0.006%

    No Known Activations