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

    Neuronpedia

    INDEX
    Explanations

    time ranges

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    線
    -0.07
     jedn
    -0.07
     Ronnie
    -0.07
     bubbles
    -0.06
     vos
    -0.06
     nez
    -0.06
     نو
    -0.06
     controllers
    -0.06
    %%
    -0.06
    father
    -0.06
    POSITIVE LOGITS
    ish
    0.06
     whereby
    0.06
    (resolve
    0.06
    휴
    0.06
    ished
    0.06
     وهو
    0.05
    スカ
    0.05
    (cal
    0.05
    ै↵
    0.05
     danmark
    0.05
    Act Density 0.003%

    No Known Activations