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

    Neuronpedia

    INDEX
    Explanations

    suppressed/inhibited

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     良
    -0.07
    düğü
    -0.07
    ileceği
    -0.06
    argins
    -0.06
     uname
    -0.06
    polate
    -0.06
    าษฎร
    -0.06
     unsustainable
    -0.06
    ("/")↵
    -0.06
     Trong
    -0.06
    POSITIVE LOGITS
     job
    0.07
     decreases
    0.07
    -pack
    0.07
     dues
    0.07
    vin
    0.06
     pore
    0.06
     rich
    0.06
     happily
    0.06
     hous
    0.06
     increases
    0.06
    Act Density 0.017%

    No Known Activations