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

    Neuronpedia

    INDEX
    Explanations

    intentions, future actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zej
    -0.07
    amental
    -0.07
     Deleg
    -0.07
     센
    -0.07
    াভাব
    -0.07
    ted
    -0.07
     dubbed
    -0.07
     특히
    -0.07
     rappel
    -0.07
     خصوص
    -0.07
    POSITIVE LOGITS
     accompl
    0.09
     enact
    0.08
     टी
    0.08
    خه
    0.08
     exactement
    0.08
     وما
    0.08
    /help
    0.07
    /look
    0.07
     criação
    0.07
     Gros
    0.07
    Act Density 0.014%

    No Known Activations