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

    Neuronpedia

    INDEX
    Explanations

    Parentheses and semicolons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Danny
    -0.07
     Davis
    -0.07
     nunca
    -0.06
    	diff
    -0.06
    zk
    -0.06
     Donna
    -0.06
     honour
    -0.06
    Nodes
    -0.06
    EHICLE
    -0.06
    Jo
    -0.06
    POSITIVE LOGITS
    链
    0.07
     Belediyesi
    0.06
     최저
    0.06
    구
    0.06
    �
    0.06
    accuracy
    0.06
    Так
    0.06
    igidbody
    0.06
    ・・・↵↵
    0.06
     seul
    0.06
    Act Density 0.049%

    No Known Activations