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

    Neuronpedia

    INDEX
    Explanations

    interceptor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    297
    -0.07
    661
    -0.07
     GOLD
    -0.06
    lang
    -0.06
     tří
    -0.06
     planners
    -0.06
    Mut
    -0.06
     下午
    -0.06
     DAO
    -0.06
    ์ล
    -0.06
    POSITIVE LOGITS
    Interceptor
    0.13
     interceptor
    0.11
     intercept
    0.09
     interception
    0.08
     Bryce
    0.08
    으면
    0.07
     injecting
    0.07
     Intercept
    0.07
     intercepted
    0.07
     kp
    0.07
    Act Density 0.001%

    No Known Activations