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

    Neuronpedia

    INDEX
    Explanations

    generals surrounding, gift card, think about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     -
    0.53
     cannot
    0.53
     aside
    0.47
    in
    0.46
     doesn
    0.45
     neither
    0.45
     from
    0.45
     between
    0.45
     around
    0.45
     in
    0.44
    POSITIVE LOGITS
    MessageNow
    0.49
     አን
    0.47
    屶
    0.46
    гах
    0.46
    јан
    0.45
    чне
    0.45
    리티
    0.45
    ڎ
    0.44
     учет
    0.44
    tble
    0.44
    Act Density 0.003%

    No Known Activations