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

    Neuronpedia

    INDEX
    Explanations

    apply to places or entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    agens
    0.47
    iciencies
    0.46
    ts
    0.45
    anded
    0.44
    ’
    0.43
    anz
    0.43
    itching
    0.43
    rices
    0.42
    ages
    0.42
    time
    0.41
    POSITIVE LOGITS
    เรา
    0.55
     mówi
    0.55
     ludzie
    0.55
     we
    0.55
     dług
    0.54
     pizza
    0.54
     мы
    0.52
     jego
    0.52
     pizzas
    0.52
     park
    0.51
    Act Density 0.000%

    No Known Activations