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

    Neuronpedia

    INDEX
    Explanations

    information and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۹
    0.79
    مل
    0.74
    ،
    0.71
    "،
    0.64
     Folge
    0.62
     आईआई
    0.61
     excepcional
    0.57
     megold
    0.57
    ك
    0.57
    ఏ
    0.57
    POSITIVE LOGITS
    a
    1.07
    <0x80>
    1.02
    ר
    1.00
    n
    0.98
    information
    0.95
    f
    0.92
     information
    0.91
    ur
    0.88
     about
    0.88
     информацию
    0.88
    Act Density 0.093%

    No Known Activations