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

    Neuronpedia

    INDEX
    Explanations

    Code installation/snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ùng
    -0.06
     hours
    -0.06
    exus
    -0.06
    第二
    -0.06
     Hours
    -0.06
    :l
    -0.06
    UserName
    -0.06
    _recipe
    -0.06
    ELEMENT
    -0.06
     Johnson
    -0.06
    POSITIVE LOGITS
     expands
    0.07
          
↵
    0.07
    		↵	↵
    0.06
     submarines
    0.06
     PARTICULAR
    0.06
     writ
    0.06
     intim
    0.06
     асп
    0.06
            
↵
    0.06
     tas
    0.06
    Act Density 0.110%

    No Known Activations