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

    Neuronpedia

    INDEX
    Explanations

    names and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﹀
    0.25
    Pyrazole
    0.24
     prost
    0.24
    ⟋
    0.23
     dSample
    0.23
    跷
    0.23
     ©️
    0.23
    竑
    0.22
     punishable
    0.22
    轧
    0.22
    POSITIVE LOGITS
    if
    0.29
    util
    0.27
    ib
    0.26
    as
    0.26
    zn
    0.25
    at
    0.25
    usa
    0.25
    ylan
    0.25
    wijl
    0.25
    z
    0.24
    Act Density 0.182%

    No Known Activations