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

    Neuronpedia

    INDEX
    Explanations

    bush followed by nouns (walking, man, fires, elephant)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਰ
    1.38
    સ
    1.22
    ا
    1.18
    т
    1.18
    swear
    1.06
    ுங்கள்
    1.05
     conjunta
    1.03
    یت
    1.02
     soir
    1.01
    iin
    1.01
    POSITIVE LOGITS
    訲
    1.11
    f
    0.88
    なぁ
    0.87
    Clik
    0.87
    0.86
    formatics
    0.84
    ah
    0.84
    年生
    0.84
     дерево
    0.83
     BYTE
    0.83
    Act Density 0.000%

    No Known Activations