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

    Neuronpedia

    INDEX
    Explanations

    (x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Doctor
    -0.08
     officer
    -0.08
     soldiers
    -0.08
     талант
    -0.08
     talent
    -0.08
    _AUTHOR
    -0.08
     Officer
    -0.07
    acula
    -0.07
     Garrett
    -0.07
    Alumno
    -0.07
    POSITIVE LOGITS
     positivity
    0.11
     positive
    0.10
     caution
    0.10
     posit
    0.10
    .Positive
    0.09
    positive
    0.09
     અર્થ
    0.09
    لاة
    0.09
     pozitiv
    0.09
     avoids
    0.08
    Act Density 0.056%

    No Known Activations