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

    Neuronpedia

    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =================================================
    -0.07
    \M
    -0.06
     брон
    -0.06
     Ου
    -0.06
    (=
    -0.06
    家伙
    -0.06
    まれ
    -0.06
    σσα
    -0.06
     Actor
    -0.06
     си
    -0.06
    POSITIVE LOGITS
     ail
    0.07
    vier
    0.07
     templates
    0.07
     ed
    0.07
     Highest
    0.07
     strate
    0.07
     boots
    0.06
    invest
    0.06
    �
    0.06
    .expect
    0.06
    Act Density 0.001%

    No Known Activations