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

    Neuronpedia

    INDEX
    Explanations

    history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spaced
    -0.06
    .parentElement
    -0.06
    average
    -0.06
    .Activity
    -0.06
    ト
    -0.06
    Na
    -0.06
    ствия
    -0.06
    interp
    -0.05
    NODE
    -0.05
    .Does
    -0.05
    POSITIVE LOGITS
     obchodní
    0.07
     Honestly
    0.07
     وإ
    0.07
    (last
    0.07
    _Check
    0.06
     Techn
    0.06
    hapus
    0.06
     interview
    0.06
    xia
    0.06
    	DECLARE
    0.06
    Act Density 0.006%

    No Known Activations