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

    Neuronpedia

    INDEX
    Explanations

    nihilism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يان
    0.38
    dominal
    0.37
    䖝
    0.37
     अकबर
    0.36
    elling
    0.36
    kam
    0.35
    thern
    0.35
    niki
    0.35
     zeal
    0.35
     typ
    0.35
    POSITIVE LOGITS
     Mih
    0.50
    ссмо
    0.44
     nih
    0.44
     Mij
    0.41
     Nih
    0.40
     нейтро
    0.40
     mih
    0.39
    чів
    0.39
    ilation
    0.38
     affirmat
    0.37
    Act Density 0.001%

    No Known Activations