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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Slow
    -0.08
     wob
    -0.07
     slow
    -0.07
     лап
    -0.07
     as
    -0.07
     godt
    -0.07
     Mozart
    -0.07
    gon
    -0.07
    oom
    -0.07
    Slow
    -0.07
    POSITIVE LOGITS
     slogans
    0.10
     regulations
    0.08
    条例
    0.08
     అధికారులు
    0.08
    -details
    0.08
    γεν
    0.08
     شعار
    0.08
    协会
    0.08
    -serv
    0.08
     قوانین
    0.08
    Act Density 0.001%

    No Known Activations