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

    Neuronpedia

    INDEX
    Explanations

    numerical identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hyperparameters
    0.18
     blotting
    0.18
     FastAPI
    0.18
     কিওয়ার্ড
    0.18
     nive
    0.18
     asymptote
    0.18
     সুবিধা
    0.17
     Sumo
    0.17
     buttercream
    0.17
     vibe
    0.17
    POSITIVE LOGITS
    7
    0.32
    2
    0.30
    6
    0.29
    8
    0.29
    j
    0.29
    4
    0.29
    5
    0.29
    9
    0.28
    uk
    0.28
    0
    0.28
    Act Density 0.095%

    No Known Activations