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

    Neuronpedia

    INDEX
    Explanations

    numbers, sodium, collection, characters, stakes, cats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     κατα
    0.48
     inductively
    0.47
     하면서
    0.47
     νο
    0.46
     과정을
    0.45
     controvers
    0.44
     식품
    0.44
    冋
    0.43
    ajaran
    0.43
     종합
    0.43
    POSITIVE LOGITS
    Cancelled
    0.52
    Push
    0.51
    Funny
    0.50
    ok
    0.50
    y
    0.49
    3
    0.49
    4
    0.48
    Tiene
    0.48
    Yes
    0.46
    detect
    0.46
    Act Density 0.000%

    No Known Activations