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

    Neuronpedia

    INDEX
    Explanations

    Collecting specific requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     защи
    0.50
    amse
    0.50
     VND
    0.49
     Manish
    0.48
    aments
    0.48
    蝮
    0.47
     lush
    0.47
     inextric
    0.47
     kaps
    0.46
     Naira
    0.46
    POSITIVE LOGITS
    \}
    0.46
    --(
    0.44
    争取
    0.44
    ?"
    0.42
    Repartition
    0.41
    Roaming
    0.41
    兽
    0.41
    lari
    0.41
    \}\
    0.41
    ueill
    0.40
    Act Density 0.000%

    No Known Activations