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

    Neuronpedia

    INDEX
    Explanations

    instructions and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BeerItem
    0.28
     squre
    0.28
    ccgi
    0.27
     mockery
    0.27
    tembre
    0.26
     quadrada
    0.26
    ोरेशन
    0.26
    🖒
    0.26
    DanhMucSP
    0.26
     renderEncoder
    0.26
    POSITIVE LOGITS
    4
    0.39
    3
    0.38
    .
    0.37
    5
    0.37
    ↵
    0.36
    -
    0.36
    0
    0.36
    1
    0.35
     The
    0.33
    *
    0.33
    Act Density 0.004%

    No Known Activations