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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NIC
    -0.07
    ísto
    -0.07
    unas
    -0.06
    Nic
    -0.06
    owan
    -0.06
     Seattle
    -0.06
     rocked
    -0.06
    生
    -0.06
    opia
    -0.06
    Encoding
    -0.06
    POSITIVE LOGITS
     appeal
    0.07
    StoryboardSegue
    0.07
            
↵        
↵
    0.06
    몰
    0.06
    -region
    0.06
    ichern
    0.06
     où
    0.06
     timer
    0.06
     Exiting
    0.06
    	append
    0.06
    Act Density 0.186%

    No Known Activations