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

    Neuronpedia

    INDEX
    Explanations

    coding forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lip
    -0.07
     Cone
    -0.07
    Fit
    -0.07
    �
    -0.07
     enumerated
    -0.07
    _DIALOG
    -0.07
    alle
    -0.07
    екар
    -0.07
    _neg
    -0.07
     Better
    -0.06
    POSITIVE LOGITS
     threadIdx
    0.06
     وما
    0.06
     ※
    0.06
    roach
    0.06
     efficiency
    0.06
     ενός
    0.06
     jam
    0.06
     téměř
    0.05
    )initWith
    0.05
    ycl
    0.05
    Act Density 0.085%

    No Known Activations