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

    Neuronpedia

    INDEX
    Explanations

    forms and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mcg
    0.39
     winning
    0.36
     პროგრამ
    0.36
     smoking
    0.36
    ◙
    0.36
    globals
    0.35
    acjach
    0.35
    elow
    0.35
    ⑧
    0.35
    ิน
    0.35
    POSITIVE LOGITS
    ворю
    0.45
     ressemble
    0.38
    કરી
    0.36
     après
    0.36
     nabíz
    0.36
    kha
    0.36
    }{|
    0.35
     auxquels
    0.35
     ainsi
    0.35
     offer
    0.34
    Act Density 0.000%

    No Known Activations