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

    Neuronpedia

    INDEX
    Explanations

    stabilization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     harvest
    -0.07
     scarce
    -0.07
     erotisk
    -0.07
    rose
    -0.07
    __()
    -0.07
     ساعت
    -0.06
     ware
    -0.06
    odě
    -0.06
    orted
    -0.06
    ěti
    -0.06
    POSITIVE LOGITS
     stabilization
    0.11
     stabilized
    0.08
    BP
    0.08
     stabil
    0.08
     stabilize
    0.08
     Starter
    0.07
    стор
    0.07
     подум
    0.07
    σω
    0.07
     aggregator
    0.07
    Act Density 0.004%

    No Known Activations