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

    Neuronpedia

    INDEX
    Explanations

    domains, Localization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    att
    0.50
     conjunto
    0.50
     synthesis
    0.46
     contemplate
    0.42
     prodigious
    0.42
     warehouse
    0.41
     mourn
    0.41
     partir
    0.41
     synthes
    0.41
    loading
    0.41
    POSITIVE LOGITS
     CommandCenter
    0.48
    殄
    0.47
    ította
    0.47
     Apparently
    0.46
     Apica
    0.46
    Restaurants
    0.45
     Locals
    0.45
     Nyl
    0.45
    协助
    0.44
     Localization
    0.44
    Act Density 0.000%

    No Known Activations