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

    Neuronpedia

    INDEX
    Explanations

    journeys and exploration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вина
    -0.07
    アイ
    -0.07
    Educ
    -0.07
     linh
    -0.07
     ولك
    -0.06
     Checker
    -0.06
    	damage
    -0.06
    Posting
    -0.06
    คอม
    -0.06
    艾
    -0.06
    POSITIVE LOGITS
     gross
    0.07
    .poly
    0.06
    porte
    0.06
     Sen
    0.06
     moved
    0.06
     recommended
    0.06
     dashed
    0.06
    antal
    0.06
     transformed
    0.06
     Economist
    0.06
    Act Density 0.078%

    No Known Activations