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

    Neuronpedia

    INDEX
    Explanations

    language prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ದ್ದರಿಂದ
    0.47
     تبدی
    0.43
     নিঃসন্দে
    0.41
     সন্ব
    0.41
     sath
    0.39
     stockno
    0.39
    gleichen
    0.39
     vasena
    0.39
     FERC
    0.39
     ಸದ
    0.38
    POSITIVE LOGITS
     me
    0.43
    5
    0.41
    Г
    0.40
    Re
    0.38
    Port
    0.38
    .
    0.38
    4
    0.38
    7
    0.38
     un
    0.37
    6
    0.37
    Act Density 0.043%

    No Known Activations