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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'aff
    -0.08
    ction
    -0.06
    егод
    -0.06
    韬
    -0.06
     tạm
    -0.06
    ATO
    -0.06
    task
    -0.06
     الشخصية
    -0.06
    OMP
    -0.06
    ess
    -0.06
    POSITIVE LOGITS
     smooth
    0.08
    业余
    0.07
     orient
    0.07
     smith
    0.07
    乱
    0.07
    sort
    0.07
     две
    0.06
     strm
    0.06
     modern
    0.06
     overturn
    0.06
    Act Density 0.010%

    No Known Activations