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

    Neuronpedia

    INDEX
    Explanations

    key pair for instances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    orma
    0.36
     Compilation
    0.36
     &_
    0.35
    adee
    0.35
     Hãy
    0.34
    থেকে
    0.34
     ✅
    0.34
     Ultimately
    0.34
     наи
    0.34
    是非常
    0.33
    POSITIVE LOGITS
     чор
    0.41
    GetKey
    0.39
     associ
    0.39
    ቢ
    0.39
    Groups
    0.39
    螻
    0.38
    ynam
    0.38
    MgCl
    0.38
    MING
    0.38
     gratuito
    0.37
    Act Density 0.001%

    No Known Activations