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

    Neuronpedia

    INDEX
    Explanations

    local transactions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Underwater
    0.45
    рг
    0.45
    Վ
    0.45
     ઝડ
    0.44
    polished
    0.43
    Nashville
    0.43
    prepare
    0.43
    黯
    0.43
    New
    0.42
    ظ
    0.42
    POSITIVE LOGITS
    y
    0.44
    z
    0.44
     walkers
    0.43
     všech
    0.43
     feedstock
    0.43
     holidays
    0.42
    azion
    0.42
     bleach
    0.42
     betracht
    0.40
    ÍC
    0.40
    Act Density 0.003%

    No Known Activations