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

    Neuronpedia

    INDEX
    Explanations

    unused variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Length
    0.47
    Rationale
    0.46
    म्
    0.46
    Narr
    0.46
    dateTime
    0.46
    Cert
    0.45
    Journey
    0.44
    Sequ
    0.43
    District
    0.43
    Cer
    0.43
    POSITIVE LOGITS
     bury
    0.48
     peripheral
    0.47
     recycle
    0.46
     peripherals
    0.46
     brink
    0.43
     perifer
    0.43
     grazing
    0.43
     eradication
    0.42
     Reuse
    0.42
    埋
    0.42
    Act Density 0.004%

    No Known Activations