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

    Neuronpedia

    INDEX
    Explanations

    paradox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _secret
    -0.07
    系統
    -0.07
     workspace
    -0.06
     kurs
    -0.06
    .Designer
    -0.06
     Discipline
    -0.06
    .Global
    -0.06
     Bhar
    -0.06
    instruction
    -0.06
     εγκα
    -0.06
    POSITIVE LOGITS
     paradox
    0.10
    adox
    0.09
     contradictions
    0.07
     Odds
    0.07
     vois
    0.07
     contradiction
    0.07
    rox
    0.07
    “
    0.06
     пох
    0.06
    pyx
    0.06
    Act Density 0.003%

    No Known Activations