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

    Neuronpedia

    INDEX
    Explanations

    at least

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inhib
    0.43
    junction
    0.42
     احتيا
    0.40
     steps
    0.40
     trials
    0.39
     syslog
    0.39
     Constants
    0.39
    yrch
    0.39
     뉴
    0.38
    मोबाइल
    0.38
    POSITIVE LOGITS
    ัต
    0.43
     lamented
    0.41
    willReturn
    0.39
    重点
    0.39
     свет
    0.38
    Kristen
    0.37
     Maria
    0.37
     نب
    0.36
    mara
    0.36
     estrogen
    0.36
    Act Density 0.000%

    No Known Activations