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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     terms
    -0.07
     saver
    -0.07
     maxlen
    -0.07
    단
    -0.06
     박
    -0.06
     transmitting
    -0.06
     broadcaster
    -0.06
    utan
    -0.06
     pulp
    -0.06
    lineno
    -0.06
    POSITIVE LOGITS
    ỹ
    0.06
    	values
    0.06
    ...↵
    0.06
    iembre
    0.06
    pill
    0.06
    103
    0.06
    TS
    0.06
    －
    0.06
     sj
    0.06
    449
    0.06
    Act Density 0.004%

    No Known Activations