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

    Neuronpedia

    INDEX
    Explanations

    true friends

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trondheim
    -0.09
     Arlington
    -0.08
     trampoline
    -0.08
     crt
    -0.08
     fantastic
    -0.08
     captcha
    -0.07
     Yosemite
    -0.07
    Tall
    -0.07
     github
    -0.07
     Getty
    -0.07
    POSITIVE LOGITS
    友情
    0.09
     selfish
    0.09
     betrayal
    0.09
     ruthless
    0.08
     comportements
    0.08
     indifferent
    0.08
     alliances
    0.08
    ibody
    0.08
     betrayed
    0.08
     verliert
    0.08
    Act Density 0.065%

    No Known Activations