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

    Neuronpedia

    INDEX
    Explanations

    Ferrari

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alpine
    0.47
    aphor
    0.42
    TimeZone
    0.41
    Radiation
    0.40
     Alpine
    0.40
     Alp
    0.40
    race
    0.39
    ᒃ
    0.39
    affirming
    0.38
     Radiation
    0.38
    POSITIVE LOGITS
     Ferrari
    0.43
     wives
    0.43
     शाहरुख
    0.42
    Ferrari
    0.41
     Cheval
    0.41
     conce
    0.41
    gherita
    0.40
     dealerships
    0.40
    赡
    0.40
     volante
    0.40
    Act Density 0.005%

    No Known Activations