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

    Neuronpedia

    INDEX
    Explanations

    Lie or Know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Life
    -0.61
    spreading
    -0.58
     spreading
    -0.53
     Know
    -0.50
     Li
    -0.48
     Provide
    -0.48
     Ha
    -0.46
     Lay
    -0.45
     Lie
    -0.44
    hdas
    -0.44
    POSITIVE LOGITS
     doubtnut
    0.83
    expandindo
    0.82
     HasFactory
    0.80
     Мексичка
    0.71
     ostavi
    0.71
     PropertyChanged
    0.70
     itſelf
    0.70
     myſelf
    0.69
    Datuak
    0.69
     Avent
    0.69
    Act Density 0.697%

    No Known Activations