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

    Neuronpedia

    INDEX
    Explanations

    increase and its outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    し
    1.62
    padă
    1.33
    จะ
    1.18
     are
    1.13
     są
    1.13
    ]，
    1.12
     کتاب
    1.10
    یت
    1.05
     août
    1.05
    】，
    1.05
    POSITIVE LOGITS
    t
    1.36
    u
    1.27
    is
    1.24
    il
    1.22
    on
    1.20
     I
    1.20
     T
    1.17
    ت
    1.16
    고
    1.07
     F
    1.06
    Act Density 0.058%

    No Known Activations