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

    Neuronpedia

    INDEX
    Explanations

    sound dismissive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    диться
    0.72
    agaman
    0.66
    usely
    0.62
    TRAILING
    0.60
     prototype
    0.60
     অনেকগুলি
    0.60
     ঘনিষ্ঠভাবে
    0.60
    OwnProperty
    0.59
     CURLE
    0.59
     prototypes
    0.59
    POSITIVE LOGITS
     indifference
    2.68
     ignore
    2.48
     ignoring
    2.45
     ignored
    2.32
    ignore
    2.24
     apathy
    2.20
     ignores
    2.20
     indifferent
    2.19
     disregard
    2.18
     oblivious
    2.11
    Act Density 0.700%

    No Known Activations