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

    Neuronpedia

    INDEX
    Explanations

    Stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mathem
    -0.08
     €/
    -0.07
    Mac
    -0.07
    vriend
    -0.07
     ξ
    -0.07
     integral
    -0.07
     anz
    -0.07
     zith
    -0.07
     sockaddr
    -0.07
     βρίσκεται
    -0.07
    POSITIVE LOGITS
     newsletters
    0.09
     teaser
    0.09
     체크
    0.09
     Persona
    0.09
     diarios
    0.09
     countdown
    0.09
    .syn
    0.09
     rutina
    0.09
     rotina
    0.09
     newsletter
    0.09
    Act Density 0.002%

    No Known Activations