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

    Neuronpedia

    INDEX
    Explanations

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Continuing
    -0.08
     hem
    -0.08
    ường
    -0.07
     Santa
    -0.07
    豳
    -0.07
    揆
    -0.07
    髀
    -0.07
    佽
    -0.07
    pop
    -0.07
    utron
    -0.07
    POSITIVE LOGITS
     Changed
    0.07
     originals
    0.07
     frightened
    0.07
     يريد
    0.07
    رعاية
    0.07
    rovers
    0.07
    打压
    0.07
    אנחנו
    0.07
     guarantee
    0.07
     defeat
    0.06
    Act Density 0.000%

    No Known Activations