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

    Neuronpedia

    INDEX
    Explanations

    Tech companies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     चलते
    -0.09
     иностран
    -0.08
    ন্স
    -0.08
     bax
    -0.08
    Celebrity
    -0.08
    qata
    -0.08
     trayectoria
    -0.08
    qrt
    -0.07
     duur
    -0.07
     আচ
    -0.07
    POSITIVE LOGITS
     GDPR
    0.08
     voluntary
    0.08
     ceremony
    0.07
     prés
    0.07
     hemisphere
    0.07
     WIN
    0.07
     préf
    0.07
     legally
    0.07
    preset
    0.07
    landing
    0.07
    Act Density 0.003%

    No Known Activations