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

    Neuronpedia

    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worldwide
    -0.08
     patriotism
    -0.07
     Over
    -0.07
    estr
    -0.07
    avr
    -0.07
    POWER
    -0.07
     over
    -0.07
     Rew
    -0.07
    otted
    -0.07
     acesso
    -0.07
    POSITIVE LOGITS
     Clinic
    0.16
     clinic
    0.14
     clinics
    0.13
    clinic
    0.10
     militia
    0.08
    Clazz
    0.08
     Chronicle
    0.07
    �
    0.07
     Bloc
    0.07
     Gazette
    0.07
    Act Density 0.003%

    No Known Activations