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

    Neuronpedia

    INDEX
    Explanations

    citations with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Mood
    0.44
     ಸುಬ್ಬ
    0.43
    Ŏ
    0.42
    ROWN
    0.42
    夂
    0.42
    InterfaceLine
    0.41
    旲
    0.41
    Benzo
    0.40
    دأ
    0.40
    ალაქ
    0.40
    POSITIVE LOGITS
    0.66
      
    0.61
    ↵↵
    0.55
     và
    0.41
    ↵
    0.40
     на
    0.40
     yaz
    0.40
     đặc
    0.39
    зи
    0.39
     и
    0.39
    Act Density 0.016%

    No Known Activations