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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Scottish
    -0.08
     JDK
    -0.07
     mmc
    -0.07
     Convert
    -0.07
     Col
    -0.07
     agre
    -0.07
     Webster
    -0.07
    ccione
    -0.07
    苔
    -0.07
    _New
    -0.06
    POSITIVE LOGITS
    就是
    0.08
    /an
    0.07
     în
    0.07
    off
    0.07
     positioned
    0.07
     closed
    0.07
    .Box
    0.06
    _filepath
    0.06
     strapped
    0.06
     Euro
    0.06
    Act Density 0.005%

    No Known Activations