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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leaks
    -0.07
     achievement
    -0.07
     بی
    -0.07
     makes
    -0.07
     coming
    -0.07
     pos
    -0.07
     Eating
    -0.06
    .elements
    -0.06
     stage
    -0.06
     overst
    -0.06
    POSITIVE LOGITS
    继续
    0.07
     sạch
    0.07
    IndexPath
    0.06
     Kurulu
    0.06
     Helpful
    0.06
    _VOID
    0.06
    mlin
    0.06
    ChartData
    0.06
    xAF
    0.06
     GCBO
    0.06
    Act Density 0.036%

    No Known Activations