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

    Neuronpedia

    INDEX
    Explanations

    LangChain and wildflowers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     on
    0.59
     de
    0.52
    0.52
     si
    0.51
    ication
    0.50
    ically
    0.50
    ical
    0.48
    ins
    0.48
    2
    0.48
     y
    0.47
    POSITIVE LOGITS
    σει
    0.61
    मिताभ
    0.61
    ቝ
    0.58
    Jwt
    0.55
    Bots
    0.54
    PropertyGroup
    0.54
    Sexo
    0.53
    ዀ
    0.53
    妆
    0.52
    Cod
    0.51
    Act Density 0.001%

    No Known Activations