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

    Neuronpedia

    INDEX
    Explanations

    that which clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diciendo
    0.43
    ⱼ
    0.42
    ikä
    0.41
     dikutip
    0.40
     Maladies
    0.38
     Couldn
    0.37
     માણ
    0.37
    幡
    0.37
     Verfü
    0.37
     rarement
    0.37
    POSITIVE LOGITS
     critics
    0.84
     officials
    0.81
     analysts
    0.80
     experts
    0.76
     proponents
    0.75
     activists
    0.68
     policymakers
    0.67
     campaigners
    0.67
     investigators
    0.66
     prosecutors
    0.66
    Act Density 0.008%

    No Known Activations