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

    Neuronpedia

    INDEX
    Explanations

    films

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Math
    -0.06
    perial
    -0.06
     Seed
    -0.06
     DIAG
    -0.06
    923
    -0.06
    .cwd
    -0.06
    Doctor
    -0.06
     Dagger
    -0.06
    lemen
    -0.06
    ilerine
    -0.06
    POSITIVE LOGITS
     turno
    0.09
    alli
    0.08
    	ar
    0.07
     imaginary
    0.06
     oasis
    0.06
    /List
    0.06
    致
    0.06
     sĩ
    0.06
    写真
    0.06
     reco
    0.06
    Act Density 0.004%

    No Known Activations