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

    Neuronpedia

    INDEX
    Explanations

    introducing new concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    awas
    0.50
    cheid
    0.48
    anlagen
    0.45
    𝚕
    0.45
    ampil
    0.45
    listOf
    0.45
    insurer
    0.44
    encias
    0.44
    мий
    0.44
     описа
    0.43
    POSITIVE LOGITS
    രു
    0.46
     và
    0.45
     إلى
    0.41
    보니
    0.41
    ；
    0.40
     mesi
    0.40
     hoặc
    0.40
     Months
    0.40
     maanden
    0.39
     Solana
    0.39
    Act Density 0.008%

    No Known Activations