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

    Neuronpedia

    INDEX
    Explanations

    Matrix dimensions/sizes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    belongs
    -0.07
     mev
    -0.07
    Over
    -0.07
    Ranked
    -0.07
     Riyadh
    -0.06
    Beauty
    -0.06
     filament
    -0.06
    "One
    -0.06
     nedeni
    -0.06
     commend
    -0.06
    POSITIVE LOGITS
    fruit
    0.06
     serializer
    0.06
    .invokeLater
    0.06
     jl
    0.06
    _testing
    0.06
     широк
    0.06
    .stringValue
    0.06
    (fi
    0.06
     Francis
    0.06
     nejd
    0.05
    Act Density 0.011%

    No Known Activations