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

    Neuronpedia

    INDEX
    Explanations

    Short codes/Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urope
    -0.07
     pipe
    -0.07
    -mail
    -0.07
    699
    -0.07
     Pipe
    -0.07
     Urban
    -0.07
     antique
    -0.06
    Auf
    -0.06
    ocache
    -0.06
    money
    -0.06
    POSITIVE LOGITS
    ea
    0.08
     Lenovo
    0.08
    ecast
    0.08
    eng
    0.08
    eri
    0.08
    elan
    0.08
    equ
    0.08
    enn
    0.08
     peas
    0.08
    elli
    0.07
    Act Density 0.629%

    No Known Activations