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

    Neuronpedia

    INDEX
    Explanations

    a/an followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ش
    1.55
     shackles
    1.44
    .
    1.44
    il
    1.42
     endeavours
    1.40
     endeavors
    1.39
    న్
    1.38
     goble
    1.38
    le
    1.36
    ో
    1.29
    POSITIVE LOGITS
     ই
    1.27
    ádz
    1.27
     є
    1.24
    s
    1.23
    Па
    1.13
    κτήθηκε
    1.12
     된
    1.10
    И
    1.10
    ウ
    1.10
    ار
    1.09
    Act Density 0.431%

    No Known Activations