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

    Neuronpedia

    INDEX
    Explanations

    arithmetic sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     עוב
    -0.08
     simpler
    -0.08
     �
    -0.07
     outside
    -0.07
     сотрудники
    -0.07
    些
    -0.07
     прошлом
    -0.07
     responsables
    -0.07
    _bucket
    -0.07
     closer
    -0.07
    POSITIVE LOGITS
     decreto
    0.08
     socialista
    0.08
    Até
    0.08
    !!!!
    0.08
    venteen
    0.08
     Resol
    0.08
    orton
    0.08
     পর্যন্ত
    0.08
     reached
    0.08
     anna
    0.08
    Act Density 0.029%

    No Known Activations