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

    Neuronpedia

    INDEX
    Explanations

    Hunter Biden or preferences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     accidens
    0.47
     impro
    0.45
     medici
    0.43
     devre
    0.42
     ڈاکٹر
    0.42
     comenta
    0.41
    apply
    0.41
    வதி
    0.40
     cun
    0.40
    わせ
    0.40
    POSITIVE LOGITS
     hateful
    0.42
    फोन
    0.41
    的项目
    0.41
    ruiter
    0.40
     phishing
    0.39
     पंजीकरण
    0.39
     или
    0.38
    图案
    0.38
     ઓછા
    0.37
     stalwart
    0.37
    Act Density 0.002%

    No Known Activations