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

    Neuronpedia

    INDEX
    Explanations

    not X but Y structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    db
    0.47
    image
    0.43
    id
    0.41
    az
    0.41
    S
    0.39
    iam
    0.38
    user
    0.38
    hope
    0.38
    can
    0.38
    if
    0.38
    POSITIVE LOGITS
     reorganize
    0.45
     rekind
    0.44
     IndexPath
    0.40
    <unused74>
    0.39
    ↗
    0.38
     whisk
    0.38
     reorganization
    0.37
     useParams
    0.37
     permeability
    0.37
     dismantling
    0.37
    Act Density 0.001%

    No Known Activations