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

    Neuronpedia

    INDEX
    Explanations

    conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /tasks
    -0.07
    不同
    -0.06
     Regents
    -0.06
    нош
    -0.06
    (Dense
    -0.06
     traces
    -0.06
    .cut
    -0.06
     Edwards
    -0.06
    opacity
    -0.06
     dropped
    -0.06
    POSITIVE LOGITS
     instruct
    0.07
    ISTR
    0.07
    	
↵	
↵
    0.06
     flirting
    0.06
    .address
    0.06
     CODE
    0.06
     jspb
    0.06
     extremist
    0.06
     év
    0.06
    lld
    0.06
    Act Density 0.007%

    No Known Activations