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

    Neuronpedia

    INDEX
    Explanations

    importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uplic
    -0.08
     northern
    -0.07
     Sul
    -0.07
     eerie
    -0.07
     microwave
    -0.07
     Uch
    -0.07
     Microwave
    -0.07
     einzigartige
    -0.07
    ud
    -0.07
     süd
    -0.07
    POSITIVE LOGITS
     ciert
    0.12
     certainly
    0.12
    ，但
    0.12
     indeed
    0.12
     있지만
    0.10
     yes
    0.10
    ，但是
    0.10
     effectivement
    0.09
     certamente
    0.09
     certes
    0.09
    Act Density 0.110%

    No Known Activations