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

    Neuronpedia

    INDEX
    Explanations

    beyond typical pairings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Zach
    0.46
    CA
    0.46
     <
    0.45
     tariffs
    0.43
     mark
    0.43
     adequacy
    0.43
    开
    0.43
     taxes
    0.42
     Antonio
    0.42
     shared
    0.42
    POSITIVE LOGITS
    avlja
    0.52
     lako
    0.52
    clud
    0.50
    quels
    0.49
    ých
    0.49
    année
    0.48
     Quỳnh
    0.48
    éli
    0.48
    傥
    0.48
    >≥</
    0.47
    Act Density 0.000%

    No Known Activations