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

    Neuronpedia

    INDEX
    Explanations

    world changing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curves
    -0.07
     adding
    -0.07
     southeast
    -0.06
    (branch
    -0.06
    Pakistan
    -0.06
    jectives
    -0.06
     Tipo
    -0.06
    (New
    -0.06
    uat
    -0.06
     igual
    -0.06
    POSITIVE LOGITS
    agog
    0.06
     whirl
    0.06
    rait
    0.06
    =val
    0.06
    śmy
    0.06
     religion
    0.06
    .Down
    0.06
    hetic
    0.06
    ulous
    0.06
    ös
    0.06
    Act Density 0.073%

    No Known Activations