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

    Neuronpedia

    INDEX
    Explanations

    Formula 1 racing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Considering
    -0.08
    -0.08
     empleado
    -0.08
     So
    -0.08
     Values
    -0.07
     "$
    -0.07
     Guitar
    -0.07
     Valor
    -0.07
     masturb
    -0.07
     aniversário
    -0.07
    POSITIVE LOGITS
    -era
    0.09
     marginalized
    0.08
    ைப்ப
    0.08
     kull
    0.08
    'époque
    0.08
     sebanyak
    0.08
    名单
    0.08
    ындағы
    0.08
    .writerow
    0.08
     ngen
    0.08
    Act Density 0.012%
    No Known Activations