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

    Neuronpedia

    INDEX
    Explanations

    code, definitions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     escaping
    -0.06
    .api
    -0.06
    Inner
    -0.06
     За
    -0.06
    .Resource
    -0.06
     skulle
    -0.06
     ελλην
    -0.06
     inside
    -0.06
    	run
    -0.06
     excel
    -0.06
    POSITIVE LOGITS
    _sep
    0.07
    +)\
    0.07
    *'
    0.07
    FIX
    0.07
    =settings
    0.06
    赫
    0.06
    欣
    0.06
     Winds
    0.06
    ssl
    0.06
    jure
    0.06
    Act Density 0.000%

    No Known Activations