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
    Section
    -0.09
     simplified
    -0.07
    .adapter
    -0.07
     sens
    -0.07
    ("^
    -0.07
     frag
    -0.06
    	test
    -0.06
     stranger
    -0.06
     CY
    -0.06
    Senator
    -0.06
    POSITIVE LOGITS
     gebruik
    0.08
    _counts
    0.08
     stark
    0.07
    ﺔ
    0.07
    โคร
    0.07
     dara
    0.07
     höch
    0.07
    _Check
    0.07
    痂
    0.07
    כנו
    0.06
    Act Density 0.001%

    No Known Activations