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

    Neuronpedia

    INDEX
    Explanations

    travel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Aud
    -0.08
    реж
    -0.07
    uning
    -0.06
    мен
    -0.06
    Mari
    -0.06
     park
    -0.06
     males
    -0.06
    HE
    -0.06
    :@
    -0.06
     male
    -0.06
    POSITIVE LOGITS
     xxx
    0.07
     Ergebn
    0.06
     accr
    0.06
     neurons
    0.06
     (£
    0.06
    .commons
    0.06
     зов
    0.06
     {:.
    0.06
    ():↵↵
    0.06
    ‫
    0.06
    Act Density 0.035%

    No Known Activations