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

    Neuronpedia

    INDEX
    Explanations

    Parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Müd
    -0.07
     спе
    -0.07
    	Status
    -0.07
    ��
    -0.06
     ALERT
    -0.06
     שש
    -0.06
    cbd
    -0.06
    flash
    -0.06
     Saudi
    -0.06
    quad
    -0.06
    POSITIVE LOGITS
    층
    0.07
     Trie
    0.07
     Hermione
    0.07
    问责
    0.07
    лон
    0.07
     floors
    0.07
     manifold
    0.07
    合理
    0.07
    ألو
    0.07
     threw
    0.07
    Act Density 0.000%

    No Known Activations