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

    Neuronpedia

    INDEX
    Explanations

    Financial terms, percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    亨
    0.43
     pembahasan
    0.40
    cdots
    0.39
     бух
    0.38
     मिनट
    0.38
     ఉత్ప
    0.38
    ắp
    0.37
     해당
    0.36
    arında
    0.36
    ረጋ
    0.36
    POSITIVE LOGITS
    کرو
    0.40
    ತೆಯ
    0.39
     प्रकृति
    0.39
    याच्या
    0.37
     quantify
    0.37
     scale
    0.36
     bil
    0.36
     stir
    0.36
     viaj
    0.36
    brock
    0.36
    Act Density 0.000%

    No Known Activations