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

    Neuronpedia

    INDEX
    Explanations

    announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mos
    -0.09
    umsy
    -0.07
     unnecessary
    -0.07
     прид
    -0.07
    �
    -0.07
    osin
    -0.07
    oczes
    -0.07
     demonstrated
    -0.07
     awkward
    -0.07
     redundant
    -0.07
    POSITIVE LOGITS
     Announces
    0.11
     announces
    0.10
    计划
    0.09
     announce
    0.09
    宣布
    0.09
    Plans
    0.08
     plannen
    0.08
     Plans
    0.08
     ঘোষণা
    0.08
     oficialmente
    0.08
    Act Density 0.129%

    No Known Activations