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

    Neuronpedia

    INDEX
    Explanations

    Joe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Lang
    -0.07
     supplying
    -0.07
     Fetch
    -0.07
     melanch
    -0.07
    eral
    -0.06
     textView
    -0.06
     Brun
    -0.06
    levard
    -0.06
     olabilir
    -0.06
    ntag
    -0.06
    POSITIVE LOGITS
     Joe
    0.22
    Joe
    0.19
     joe
    0.12
     Jake
    0.09
     Pete
    0.08
     Jim
    0.08
    ASTE
    0.07
     JFK
    0.07
    450
    0.07
    oe
    0.07
    Act Density 0.002%

    No Known Activations