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

    Neuronpedia

    INDEX
    Explanations

    language, observer, chickens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     configur
    0.51
     stabilizes
    0.50
     delivers
    0.48
    ﭼ
    0.46
     durata
    0.46
     tecla
    0.46
     organizes
    0.45
     dizi
    0.44
     misses
    0.44
     deliveries
    0.44
    POSITIVE LOGITS
    Items
    0.53
    вали
    0.52
    Auth
    0.48
    Virus
    0.47
    items
    0.46
    iology
    0.46
    Identity
    0.46
    OR
    0.45
    Map
    0.45
    Raw
    0.45
    Act Density 0.001%

    No Known Activations